© 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. 9856
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    rale
    -0.32
     horns
    -0.28
     reflected
    -0.28
    kie
    -0.27
     stem
    -0.27
    ä¸ĭ乡
    -0.26
    éĶī
    -0.26
    侬
    -0.25
    éĽģ
    -0.25
    rell
    -0.25
    POSITIVE LOGITS
    ä¸Ģå°ģ
    0.29
    .inject
    0.28
     Carpenter
    0.27
    ::.
    0.26
     Manip
    0.26
    æŃ¹
    0.25
    é¢Ħå¤ĩ
    0.25
    -empty
    0.25
    讨论
    0.25
    åįıè®®
    0.25
    Activations Density 0.002%

    No Known Activations