© 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. 42151
    Prev
    Next
    INDEX
    Explanations

    manual

    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
    æ§Ľ
    -0.25
    iant
    -0.25
    igure
    -0.24
    èĢĥåı¤
    -0.24
    饰
    -0.23
    é£Łçī©
    -0.23
    /*================================================================
    -0.23
     MONEY
    -0.23
    è³´
    -0.23
    Arg
    -0.22
    POSITIVE LOGITS
     manual
    1.69
     Manual
    1.53
    manual
    1.46
    Manual
    1.42
    _manual
    1.27
    æīĭåĬ¨
    1.27
     MANUAL
    1.25
     manually
    1.16
    .manual
    1.13
    /manual
    1.03
    Activations Density 0.013%

    No Known Activations