© 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. 95906
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     momentum
    -0.52
     resultant
    -0.50
     Momentum
    -0.45
     vector
    -0.42
    moment
    -0.42
    çŁ¢
    -0.41
     kinetic
    -0.40
    vector
    -0.39
     vectors
    -0.36
     impulse
    -0.36
    POSITIVE LOGITS
    GST
    0.28
     büt
    0.28
    ambre
    0.28
     detach
    0.27
    åIJİéĿ¢çļĦ
    0.27
    lm
    0.26
     AMS
    0.26
    è¿ĻåĿĹ
    0.26
    detach
    0.25
    æİ¥åĬĽ
    0.25
    Activations Density 0.891%

    No Known Activations