© 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. 7146
    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
    åĨį
    -0.31
    rist
    -0.29
    èģĶ
    -0.27
    è¶Ĭ
    -0.26
    agers
    -0.25
    >{"
    -0.25
     fragile
    -0.24
     apex
    -0.24
     refl
    -0.24
    getPost
    -0.24
    POSITIVE LOGITS
    lke
    0.29
    udeau
    0.26
    dar
    0.26
    é¢Ĺç²Ĵ
    0.25
    èĸı
    0.25
     Swagger
    0.25
     Manson
    0.24
     RETURNS
    0.24
    çľĭçĶµè§Ĩ
    0.24
    çľĭå¾Ĺ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.