© 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. 41872
    Prev
    Next
    INDEX
    Explanations

    the

    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
     rest
    -0.47
    rest
    -0.45
    ä½Ļ
    -0.42
    Rest
    -0.42
     Rest
    -0.42
    (rest
    -0.35
    /rest
    -0.35
     rests
    -0.32
    _rest
    -0.32
    PA
    -0.31
    POSITIVE LOGITS
    åīįä¸Ģ天
    0.28
    elu
    0.27
    è¿Ļä¹Ī说
    0.26
    çĪ¸çĪ¸å¦Īå¦Ī
    0.26
    åīįä¸ī
    0.26
     slog
    0.26
     commute
    0.26
    åľ¨æѤä¹ĭåīį
    0.26
     pandemic
    0.26
     earlier
    0.26
    Activations Density 0.006%

    No Known Activations