© 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. 15-RESID-POST-AA
    6. 43246
    Prev
    Next
    INDEX
    Explanations

    code

    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
    _DYNAMIC
    -0.06
     apo
    -0.06
     Arena
    -0.06
    爆炸
    -0.06
    Task
    -0.06
    לית
    -0.06
     IsActive
    -0.06
    fi
    -0.06
    |#
    -0.06
    PROGRAM
    -0.06
    POSITIVE LOGITS
     Africans
    0.08
     getColumn
    0.07
    liğ
    0.07
     slaves
    0.07
    毫升
    0.07
    姑娘
    0.07
     influences
    0.07
     whistlebl
    0.07
     squares
    0.07
    (code
    0.07
    Activations Density 0.009%

    No Known Activations