© 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. 7569
    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
    åıł
    -0.28
     Brief
    -0.26
    returnValue
    -0.24
    AccessException
    -0.24
    conde
    -0.24
    imon
    -0.24
    éĩįå·¥
    -0.23
    >Edit
    -0.23
    apl
    -0.23
     singleton
    -0.23
    POSITIVE LOGITS
     duk
    0.28
    为èĩªå·±
    0.27
     cro
    0.27
     Stick
    0.25
    ä¸į代表
    0.25
    å®īåħ¨äºĭæķħ
    0.24
    istine
    0.24
    女人
    0.24
     stick
    0.24
    -minded
    0.24
    Activations Density 0.444%

    No Known Activations

    This feature has no known activations.