© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 30736
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    segments that mark or start a forum-style question or answer (e.g., "Q:", "A:", "First.", "Short answer:", and other Q/A or section-introducing lines).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    耔
    -0.07
     bullish
    -0.07
     *))
    -0.07
     ProgressBar
    -0.06
    стью
    -0.06
    ㌠
    -0.06
    㰀
    -0.06
     assays
    -0.06
    .handleChange
    -0.06
    _True
    -0.06
    POSITIVE LOGITS
    居室
    0.08
    wallet
    0.07
    婆婆
    0.07
     component
    0.07
    �
    0.07
     components
    0.07
    --------↵↵
    0.07
    基础设施
    0.07
    小孩子
    0.07
    メンバー
    0.07
    Activations Density 0.068%

    No Known Activations