© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6860
    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
    æģ¢å¤įæŃ£å¸¸
    -0.26
    ypi
    -0.26
    ieber
    -0.25
    eva
    -0.25
     embarked
    -0.25
     dicts
    -0.24
     Sugar
    -0.24
     Invent
    -0.23
    è¦ģ好好
    -0.23
     AVC
    -0.23
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.29
     sibling
    0.27
    ä¿ĿçķĻ
    0.26
     cuid
    0.26
    å¾Ĵ
    0.25
    (^
    0.24
    ocator
    0.23
    imilar
    0.23
    rior
    0.23
    een
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.