© 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. 24-TRANSCODER-HP
    7. 150110
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {}.
    -0.28
    ãĤ¨ãĥ³
    -0.28
    ITAL
    -0.26
    ital
    -0.26
     $$
    -0.26
     MS
    -0.26
    å·¥ç¨ĭ
    -0.25
    engine
    -0.25
    asn
    -0.25
     ohio
    -0.25
    POSITIVE LOGITS
    embro
    0.26
    ç«ĭ
    0.25
    umba
    0.24
    (para
    0.24
     Morocco
    0.24
    umat
    0.24
    è§Į
    0.23
     lap
    0.23
    /se
    0.23
    uffle
    0.23
    Activations Density 1.353%

    No Known Activations

    This feature has no known activations.