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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13335
    Prev
    Next
    INDEX
    Explanations

    his

    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
    .drawRect
    -0.08
    ㄡ
    -0.08
     quali
    -0.07
    我可以
    -0.07
     Drake
    -0.07
    weeney
    -0.07
    间
    -0.07
    please
    -0.07
    ula
    -0.07
     Maggie
    -0.07
    POSITIVE LOGITS
     his
    0.10
     His
    0.08
     العسكري
    0.07
     �
    0.07
     rinse
    0.07
    š
    0.07
    -no
    0.07
     مو
    0.07
     nhạc
    0.07
     serious
    0.07
    Activations Density 0.105%

    No Known Activations