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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    6. 40449
    Prev
    Next
    INDEX
    Explanations

    ی

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fast
    -0.07
    ってくる
    -0.07
    loop
    -0.06
    起源
    -0.06
    Monitor
    -0.06
     стан
    -0.06
    EXP
    -0.06
    チェ
    -0.06
     heck
    -0.06
    -stage
    -0.06
    POSITIVE LOGITS
     columnName
    0.08
     getMenu
    0.07
     일
    0.07
     medio
    0.07
    Japanese
    0.07
    '/>↵
    0.07
     admon
    0.07
     Father
    0.07
     RES
    0.07
    冉
    0.07
    Activations Density 0.008%

    No Known Activations