© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19876
    Prev
    Next
    INDEX
    Explanations

    anti- prefix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    readonly
    -0.26
    uncture
    -0.26
    .fake
    -0.25
     dropout
    -0.25
    cope
    -0.25
    tryside
    -0.25
     (('
    -0.24
     ta
    -0.24
    verty
    -0.24
     Riv
    -0.24
    POSITIVE LOGITS
    åĹ¡
    0.27
     veget
    0.26
    ä¹ĭåĬ¿
    0.25
    assin
    0.24
    æŁ¥çľĭ详æĥħ
    0.24
    .ws
    0.24
     Dani
    0.24
    signal
    0.24
     mess
    0.24
    signals
    0.23
    Activations Density 0.015%

    No Known Activations