© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14637
    Prev
    Next
    INDEX
    Explanations

    SEC releases

    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
     isbn
    -0.08
    J
    -0.07
     hugely
    -0.07
     slang
    -0.06
    下载
    -0.06
    <|im_start|>
    -0.06
    .Tasks
    -0.06
    ipi
    -0.06
    inscription
    -0.06
    NN
    -0.06
    POSITIVE LOGITS
    (Point
    0.08
     dei
    0.08
     Casual
    0.07
    Physical
    0.07
     Mu
    0.07
    Floating
    0.07
     Homes
    0.07
    edelta
    0.07
    PropertyValue
    0.07
    .Matrix
    0.07
    Activations Density 0.012%

    No Known Activations