© 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. 76471
    Prev
    Next
    INDEX
    Explanations

    René Magritte

    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
     Nes
    -0.08
    Liver
    -0.08
    <|im_end|>
    -0.07
     cropped
    -0.07
    Backdrop
    -0.07
    (eventName
    -0.07
     Filme
    -0.07
    💏
    -0.07
    煟
    -0.07
    比较好
    -0.07
    POSITIVE LOGITS
    alk
    0.07
     restr
    0.07
    יצו
    0.07
     задач
    0.07
    -scale
    0.07
    holds
    0.07
    bk
    0.07
    经理
    0.07
    又
    0.07
    thers
    0.07
    Activations Density 0.002%

    No Known Activations