© 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. 141334
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    qual
    -0.25
    	glut
    -0.25
    RenderingContext
    -0.24
    uko
    -0.24
     HttpClientModule
    -0.24
    ician
    -0.23
     tá»Ļc
    -0.23
    tokenId
    -0.23
    WebHost
    -0.23
    ä¸ĵåįĸ
    -0.23
    POSITIVE LOGITS
     schedules
    0.27
    çŁŃ缺
    0.26
    ä»Ļ
    0.26
    èĬ±å¼Ģ
    0.26
    hdr
    0.26
    åħ¬ç¤º
    0.26
    ErrorException
    0.25
    /doc
    0.25
     shortfall
    0.24
     schedule
    0.24
    Activations Density 3.822%

    No Known Activations