© 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. 42589
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific, and code examples

    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
    èĩ´
    -0.27
    è®°
    -0.26
    æİı
    -0.25
    çľ¼åīįçļĦ
    -0.24
    ute
    -0.24
    itzer
    -0.24
    涨
    -0.23
    Ỽt
    -0.23
    .SC
    -0.23
    uchi
    -0.23
    POSITIVE LOGITS
    aclass
    0.54
    amodel
    0.52
    acom
    0.49
    apro
    0.49
    abox
    0.48
    aN
    0.47
    ac
    0.46
    abr
    0.46
    agraph
    0.45
    aw
    0.45
    Activations Density 0.042%

    No Known Activations