© 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. 63321
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åªĴä½ĵæĬ¥éģĵ
    -0.26
    лÑij
    -0.25
    hdl
    -0.24
    èijĹ
    -0.24
    éĹ¨æ§Ľ
    -0.24
    æĶ¸
    -0.24
    åħįçĸ«åĬĽ
    -0.24
    opic
    -0.23
    leep
    -0.23
     Contributors
    -0.23
    POSITIVE LOGITS
    শ
    0.25
    ÙĦاÙģ
    0.24
     deg
    0.24
    çīĮ
    0.23
    semb
    0.23
     wastes
    0.23
    -inc
    0.23
    mination
    0.23
     disap
    0.23
    åĮ»ç§ij大åѦ
    0.23
    Activations Density 1.067%

    No Known Activations

    This feature has no known activations.