© 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. 108297
    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
     dec
    -0.30
    race
    -0.30
    rac
    -0.27
     poc
    -0.26
    åħ·
    -0.26
    _dec
    -0.26
    acus
    -0.25
    -Dec
    -0.24
    owell
    -0.24
    metic
    -0.24
    POSITIVE LOGITS
    ibox
    0.31
    åıijå¸ĥä¼ļä¸Ĭ
    0.26
    olvers
    0.26
    ç½ijç»ľä¼łæĴŃ
    0.25
     supers
    0.25
    uls
    0.25
    iro
    0.25
    Stra
    0.25
    äºĨåĩºæĿ¥
    0.24
    æ³ķåħ°
    0.23
    Activations Density 0.303%

    No Known Activations

    This feature has no known activations.