© 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. 8872
    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
    è°ĭ
    -0.28
    stry
    -0.26
    aylor
    -0.25
    æ¶ī足
    -0.25
    ãģĬåĭ§ãĤģ
    -0.25
     hại
    -0.24
    abal
    -0.24
    cream
    -0.24
    ADVERTISEMENT
    -0.24
    ulkan
    -0.24
    POSITIVE LOGITS
    å¿Ĺ
    0.26
    iven
    0.26
    /Object
    0.25
    given
    0.24
    goo
    0.24
    csr
    0.24
    _except
    0.23
    antic
    0.23
     coma
    0.23
    according
    0.23
    Activations Density 0.053%

    No Known Activations

    This feature has no known activations.