© 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. 19-TRANSCODER-HP
    7. 7731
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lick
    -0.30
    eses
    -0.27
     cioè
    -0.24
    esModule
    -0.24
     baÅŁÄ±nda
    -0.23
     H
    -0.23
     getContext
    -0.23
    XObject
    -0.23
    Exc
    -0.23
    ä¸Ĭä¸ĭ
    -0.23
    POSITIVE LOGITS
    çıł
    0.27
    ç©·
    0.25
    ThreadId
    0.25
    kar
    0.25
    agger
    0.24
     improvis
    0.23
    Ĥ¬
    0.23
    ĸī
    0.23
     WM
    0.23
    大æ¦Ĥæĺ¯
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.