© 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. 30-TRANSCODER-HP
    7. 95445
    Prev
    Next
    INDEX
    Explanations

    names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Till
    -0.28
    é£ŀ
    -0.27
     POW
    -0.27
    Ĥ¬
    -0.26
    ework
    -0.26
     Cabin
    -0.25
    é£Ľ
    -0.25
    stat
    -0.25
     ik
    -0.25
     flying
    -0.24
    POSITIVE LOGITS
    ç»Ļèĩªå·±
    0.27
    chie
    0.27
    çĦľ
    0.26
    è§
    0.26
    cce
    0.26
    urement
    0.26
    arme
    0.25
    uating
    0.25
    è··
    0.25
    *[
    0.25
    Activations Density 0.002%

    No Known Activations