© 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. 41518
    Prev
    Next
    INDEX
    Explanations

    vine

    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
     sil
    -0.27
    èģĶè°Ĭ
    -0.27
    zers
    -0.26
    ç»ĵæĻ¶
    -0.26
    thood
    -0.26
     Sor
    -0.25
    abis
    -0.25
    _STRIP
    -0.25
    field
    -0.25
    ctors
    -0.25
    POSITIVE LOGITS
    aty
    0.31
    ä¼IJ
    0.31
    yen
    0.27
    延伸
    0.25
    ä¿ĿçķĻ
    0.24
     `-
    0.24
    explicit
    0.24
    P
    0.24
     IDM
    0.24
    å¾ĭ
    0.24
    Activations Density 0.001%

    No Known Activations