© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 57171
    Prev
    Next
    INDEX
    Explanations

    question answering

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imdi
    -0.08
    ่ว
    -0.07
    Jeste
    -0.07
    faith
    -0.07
     deline
    -0.07
     Extr
    -0.07
    _eta
    -0.06
     увер
    -0.06
    ysize
    -0.06
    ⴻ
    -0.06
    POSITIVE LOGITS
     kit
    0.08
    ("$.
    0.07
    笑笑
    0.07
    תכ
    0.07
    oting
    0.07
    谈话
    0.07
    她们
    0.07
    :convert
    0.07
    Registrar
    0.06
    ضة
    0.06
    Activations Density 0.037%

    No Known Activations