© 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. 95826
    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
    licate
    -0.34
    renal
    -0.27
    lica
    -0.27
    ä»ĸçļĦ
    -0.26
    awning
    -0.26
     afr
    -0.25
    oph
    -0.25
    tor
    -0.24
    renders
    -0.24
    åĦĨ
    -0.24
    POSITIVE LOGITS
     constituency
    0.27
    [cell
    0.27
    ãĤħ
    0.27
     spl
    0.27
    spl
    0.26
    cells
    0.26
    AuthToken
    0.25
    å°Ĭæķ¬
    0.25
    ç»Ĩ
    0.25
    Cells
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.