© 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. 95501
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ulin
    -0.32
     cuffs
    -0.30
    mpl
    -0.27
    ä¸įå®Į
    -0.26
     surviving
    -0.26
     Cult
    -0.25
    Äĥr
    -0.25
    .ins
    -0.24
    uli
    -0.24
    è¢«åĽ°
    -0.24
    POSITIVE LOGITS
    æĭĽ
    0.29
     addressed
    0.28
    itizer
    0.27
    itized
    0.26
     valu
    0.25
    éķĩ
    0.25
    yped
    0.25
    ä¼°
    0.25
     mult
    0.24
    st
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.