© 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. 11-RESID-POST-AA
    6. 29719
    Prev
    Next
    INDEX
    Explanations

    merit

    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
    较高
    -0.07
    估值
    -0.07
    相较
    -0.07
    淡水
    -0.07
     incredibly
    -0.07
    elts
    -0.06
     Bones
    -0.06
     Hicks
    -0.06
    cretion
    -0.06
    inton
    -0.06
    POSITIVE LOGITS
     produit
    0.08
    Directory
    0.07
    福
    0.07
    clientes
    0.07
    刀
    0.07
     Substance
    0.07
    pl
    0.07
     dig
    0.07
    \">";↵
    0.07
    裸
    0.07
    Activations Density 0.005%

    No Known Activations