© 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. 8632
    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
     overhaul
    -0.27
    losed
    -0.26
    æ¼Ķç»İ
    -0.25
    tu
    -0.25
    ('~
    -0.25
    éľ²åĩº
    -0.25
     openly
    -0.24
     broadcasts
    -0.24
     çıkar
    -0.23
    scale
    -0.23
    POSITIVE LOGITS
    adier
    0.28
    ugh
    0.26
    é¼»
    0.25
    зеÑĢ
    0.25
    anh
    0.25
    erah
    0.24
    ä¸ģ
    0.24
    ä¸Ļ
    0.24
    LET
    0.23
     BH
    0.23
    Activations Density 0.125%

    No Known Activations

    This feature has no known activations.