© 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. 8666
    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
    人群
    -0.27
     MessageType
    -0.26
    |i
    -0.26
     \%
    -0.26
    º«
    -0.26
    èIJ¥éĢłèī¯å¥½
    -0.25
     %@
    -0.25
     Portal
    -0.24
    larg
    -0.24
    amodel
    -0.24
    POSITIVE LOGITS
    reau
    0.32
    æĻ¯
    0.30
    ablo
    0.29
     sendo
    0.28
    tered
    0.26
     src
    0.26
    $obj
    0.25
     Tender
    0.25
    å§Ķ
    0.25
     mù
    0.25
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.