© 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. 88479
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    esh
    -0.31
     producing
    -0.28
    ä¸Ģå¤ľ
    -0.26
    åĩij
    -0.26
    ç«ĭ
    -0.25
    ")+
    -0.25
    éħĴä¸ļ
    -0.25
     produce
    -0.25
    ıyla
    -0.25
    rega
    -0.25
    POSITIVE LOGITS
    HasBeen
    0.26
    åıĪ被
    0.25
     backstage
    0.25
    nger
    0.24
    é¢ı
    0.24
    éĺģ
    0.24
     kla
    0.23
    oundation
    0.23
    hooks
    0.23
    éĥ½æĺ¯éĿŀ常
    0.23
    Activations Density 50.832%

    No Known Activations