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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39284
    Prev
    Next
    INDEX
    Explanations

    carc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±Ģéĥ¨
    -0.27
    mise
    -0.26
    éģĵçIJĨ
    -0.25
    ä¿ĦåĽ½
    -0.25
    isty
    -0.25
    åŀ£
    -0.25
    isce
    -0.25
    ury
    -0.25
    hay
    -0.24
    åı£æ°Ķ
    -0.24
    POSITIVE LOGITS
    emens
    0.30
    pra
    0.28
     Roma
    0.27
    asso
    0.27
    PEC
    0.27
    /apps
    0.26
    romo
    0.25
    culo
    0.25
    edes
    0.25
    loat
    0.25
    Activations Density 0.371%

    No Known Activations