© 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. 18-TRANSCODER-HP
    7. 88194
    Prev
    Next
    INDEX
    Explanations

    /wiki

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /browse
    -0.30
    NER
    -0.25
     meant
    -0.25
    ington
    -0.25
     wilt
    -0.24
     REV
    -0.24
    âīª
    -0.24
    ament
    -0.24
    åIJĪæł¼
    -0.23
    æł¼å°Ķ
    -0.23
    POSITIVE LOGITS
    ENN
    0.30
    ä¸ĭåİ»
    0.28
    _FRAGMENT
    0.28
    rush
    0.28
    çļĦè¶ĭåĬ¿
    0.28
     betrayed
    0.26
    visa
    0.26
    fr
    0.26
    è¶
    0.25
    è¿İæĿ¥
    0.25
    Activations Density 2.671%

    No Known Activations