© 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. 39322
    Prev
    Next
    INDEX
    Explanations

    technical subjects

    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
    a
    -0.38
    а
    -0.35
    iese
    -0.27
    ie
    -0.26
    ylene
    -0.26
     therm
    -0.25
    ge
    -0.24
    ict
    -0.24
    ilde
    -0.24
    é¢Ĥ
    -0.24
    POSITIVE LOGITS
    anut
    0.26
    _bs
    0.26
    antar
    0.25
    uttle
    0.25
    assium
    0.25
    KR
    0.24
    -archive
    0.24
    antt
    0.23
    kı
    0.23
    almart
    0.23
    Activations Density 1.256%

    No Known Activations