© 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. 32-TRANSCODER-HP
    7. 43129
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŀļ
    -0.27
    ç¼Ŀ
    -0.25
    ç¿»
    -0.25
     Operation
    -0.25
    ents
    -0.24
    ç¼ĿéļĻ
    -0.24
    sent
    -0.24
    tape
    -0.24
     Kent
    -0.24
    çŁŃ
    -0.24
    POSITIVE LOGITS
    iform
    0.29
    \GeneratedValue
    0.28
    ders
    0.27
    æĺ´
    0.26
    .il
    0.26
    IFORM
    0.25
    gos
    0.24
    表æī¬
    0.24
    龸çİĭ
    0.24
    ecess
    0.23
    Activations Density 0.000%

    No Known Activations