© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    minimum

    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
    pery
    -0.30
    edom
    -0.26
    inox
    -0.26
    ViewItem
    -0.25
    该éĻ¢
    -0.25
    éĺĬ
    -0.25
    红èĮ¶
    -0.25
    è¶ĬãģĹ
    -0.24
     chilled
    -0.24
    çıª
    -0.24
    POSITIVE LOGITS
    s
    0.40
    æĸ¯åĿ¦
    0.28
     host
    0.28
    poi
    0.27
     poi
    0.27
    sad
    0.26
     gain
    0.26
     feliz
    0.26
    ili
    0.26
    ac
    0.25
    Activations Density 0.003%

    No Known Activations