© 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. 43681
    Prev
    Next
    INDEX
    Explanations

    high

    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
    essel
    -0.27
    .intValue
    -0.26
    UED
    -0.25
    åįķä»·
    -0.25
    å¼ĢéĢļ
    -0.25
    ndon
    -0.24
     nh
    -0.24
    ponsored
    -0.24
    å½Ĵ纳
    -0.24
    EObject
    -0.23
    POSITIVE LOGITS
     High
    0.37
    é«ĺ
    0.35
    High
    0.35
     high
    0.32
    ä¿Ŀ
    0.30
    high
    0.29
     HIGH
    0.28
    å¥ĩ
    0.28
    aud
    0.28
    _high
    0.27
    Activations Density 0.005%

    No Known Activations