© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 106886
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    heck
    -0.33
    åıĪèĥ½
    -0.29
     NOTICE
    -0.27
    è´¨
    -0.27
    éģ
    -0.26
     License
    -0.25
    iero
    -0.25
     heraus
    -0.25
    æĬľ
    -0.25
    ceu
    -0.25
    POSITIVE LOGITS
    è¿Ļ个éĹ®é¢ĺ
    0.29
    omatic
    0.28
    urator
    0.27
    主è¦ģåİŁåĽł
    0.26
    elon
    0.26
    omat
    0.25
    åħ·ä½ĵæĥħåĨµ
    0.25
    logger
    0.25
    _OM
    0.25
    è¿Ļç§įæĥħåĨµ
    0.25
    Activations Density 11.550%

    No Known Activations