© 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. 8814
    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
    çīĪæĿĥæīĢæľī
    -0.27
     départ
    -0.25
    alon
    -0.25
    SPATH
    -0.25
    è¿Ļ个åIJįåŃĹ
    -0.25
    èĩ§
    -0.25
    .fromString
    -0.24
    骷
    -0.24
     legally
    -0.24
    .setRequest
    -0.24
    POSITIVE LOGITS
    å±¹
    0.33
    åı¯è§ģ
    0.26
    (--
    0.26
    ibir
    0.26
     trusted
    0.25
    VI
    0.25
    çªĹæĪ·
    0.25
    stri
    0.25
     Shepherd
    0.24
    æĭĵ
    0.24
    Activations Density 0.364%

    No Known Activations

    This feature has no known activations.