© 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. 95370
    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
    è¿ľæĻ¯
    -0.27
    orque
    -0.25
    sez
    -0.25
    askan
    -0.24
    bsite
    -0.24
    ext
    -0.24
    åīįæıIJæĺ¯
    -0.24
     polo
    -0.23
    eps
    -0.23
    èĩ´
    -0.23
    POSITIVE LOGITS
     onSubmit
    0.28
    .onSubmit
    0.27
    -wrap
    0.26
    åĵĩ
    0.26
    /respond
    0.25
    _WRAP
    0.24
     grown
    0.24
    Wrap
    0.24
     oh
    0.24
    aval
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.