© 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. 58393
    Prev
    Next
    INDEX
    Explanations

    Article/title context

    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
     Genius
    -0.28
    ns
    -0.28
    ENSE
    -0.27
    çŃ¹çłģ
    -0.25
     ns
    -0.25
    çĿ¿
    -0.24
    å¹Ħ
    -0.24
    containers
    -0.24
    breadcrumbs
    -0.24
    æĸĹäºī
    -0.23
    POSITIVE LOGITS
     flare
    0.29
    å®īåħ¨æĢ§
    0.27
    åĽŃ
    0.27
    .getProperties
    0.25
    Tre
    0.25
    mites
    0.24
     Independence
    0.24
    (exports
    0.23
     Steele
    0.23
    å¤ļåħĥ
    0.23
    Activations Density 0.882%

    No Known Activations