© 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. 43845
    Prev
    Next
    INDEX
    Explanations

    mixed sources with code/quotes

    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
     cast
    -0.78
    Cast
    -0.71
     Cast
    -0.70
    cast
    -0.66
     casting
    -0.63
     casts
    -0.62
     CAST
    -0.59
    casting
    -0.59
    CAST
    -0.59
    _cast
    -0.57
    POSITIVE LOGITS
    pons
    0.29
     tracing
    0.28
    Lint
    0.26
    ertia
    0.25
    ys
    0.25
    çĽ¸å¯¹è¾ĥ
    0.25
    irected
    0.24
    (document
    0.24
    Comm
    0.24
    visor
    0.24
    Activations Density 0.004%

    No Known Activations