Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61800
    Prev
    Next
    INDEX
    Explanations

    Won

    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
     fibre
    -0.07
     supplies
    -0.07
    加班
    -0.06
    .IS
    -0.06
     suspense
    -0.06
     trench
    -0.06
    ”;
    -0.06
     tq
    -0.06
     tread
    -0.06
    不小的
    -0.06
    POSITIVE LOGITS
    anim
    0.09
     won
    0.08
    .serialization
    0.08
    won
    0.07
    亡
    0.07
    WO
    0.07
     Vict
    0.07
    劳动合同
    0.07
    淹没
    0.07
    鸮
    0.07
    Activations Density 0.012%

    No Known Activations