© 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. 27-TRANSCODER-HP
    7. 7813
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     since
    -0.31
    since
    -0.29
    enas
    -0.28
    idden
    -0.27
     Garland
    -0.26
    åĽłä¸ºæĪij们
    -0.26
    Since
    -0.26
    ases
    -0.25
    ignite
    -0.25
    vi
    -0.24
    POSITIVE LOGITS
     results
    0.40
    ç»ĵæŀľæĺ¾ç¤º
    0.38
    (results
    0.36
    results
    0.36
    _RESULTS
    0.34
     resultados
    0.33
    çłĶ究æĬ¥åijĬ
    0.33
    ç»ĵæŀľ
    0.33
    .results
    0.32
    æݧåĪ¶
    0.31
    Activations Density 0.002%

    No Known Activations