© 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. 130709
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    dle
    -0.26
    Dire
    -0.25
    å®ŀè·µç»ıéªĮ
    -0.25
    fait
    -0.24
    unks
    -0.24
    azzo
    -0.24
    大åĬĽ
    -0.24
    oblin
    -0.23
     thủ
    -0.23
    uly
    -0.23
    POSITIVE LOGITS
    管çIJĨä¸Ńå¿ĥ
    0.27
    ERV
    0.27
    ump
    0.25
    оÑģÑĤи
    0.24
     Correction
    0.23
     Toll
    0.23
    irling
    0.23
    xca
    0.23
     sworn
    0.23
     dominating
    0.23
    Activations Density 1.178%

    No Known Activations