Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45588
    Prev
    Next
    INDEX
    Explanations

    pur

    np_max-act · gemini-2.0-flash
    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
     parametros
    -0.07
    .Framework
    -0.07
    صندوق
    -0.07
    .steps
    -0.07
    🕸
    -0.07
    ཛ
    -0.07
     совершенно
    -0.07
    นำมา
    -0.07
     משחקי
    -0.07
    מעצב
    -0.07
    POSITIVE LOGITS
    國內
    0.07
    (hour
    0.07
     IDisposable
    0.07
    鬲
    0.07
     fend
    0.06
    锞
    0.06
     emptied
    0.06
    幼儿园
    0.06
    constexpr
    0.06
     HttpServletRequest
    0.06
    Activations Density 0.005%

    No Known Activations