© 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. 14-TRANSCODER-HP
    7. 40877
    Prev
    Next
    INDEX
    Explanations

    Europe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    订éĺħ
    -0.27
    æķ°æݧ
    -0.27
    .eu
    -0.26
    ¦
    -0.25
    åĴĮ个人
    -0.25
    éķĹ
    -0.25
    numeric
    -0.24
     dragons
    -0.23
    è·Łè¸ª
    -0.23
    ża
    -0.23
    POSITIVE LOGITS
    åīįæīĢ
    0.29
    IVER
    0.27
    临
    0.25
    unate
    0.25
    .Photo
    0.24
    unan
    0.24
    åįİ举
    0.24
    iver
    0.24
    pray
    0.24
    PU
    0.23
    Activations Density 0.412%

    No Known Activations