© 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. 20-TRANSCODER-HP
    7. 130599
    Prev
    Next
    INDEX
    Explanations

    Legal/Bureaucratic contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢаз
    -0.27
    gebra
    -0.26
    rage
    -0.26
    纵
    -0.24
     Rath
    -0.24
     sant
    -0.24
    razier
    -0.24
    ç»ıéªĮåĴĮ
    -0.24
    /utils
    -0.23
    ntax
    -0.23
    POSITIVE LOGITS
    âĿij
    0.26
     BLUE
    0.26
    _Pin
    0.24
    igham
    0.24
    liner
    0.24
    itia
    0.24
     Bingo
    0.23
    LN
    0.23
    åĽŀäºĭ
    0.23
    enton
    0.23
    Activations Density 3.525%

    No Known Activations