© 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. 32-TRANSCODER-HP
    7. 44114
    Prev
    Next
    INDEX
    Explanations

    paper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     accumulator
    -0.27
    è·Łå¥¹
    -0.26
    æĬ¬
    -0.26
    éħįå¥Ĺ
    -0.26
    fläche
    -0.25
    .times
    -0.25
    ocha
    -0.24
    CTIONS
    -0.24
    erox
    -0.23
    ulpt
    -0.23
    POSITIVE LOGITS
     dealing
    0.50
     deals
    0.44
     deal
    0.43
     dealt
    0.42
    deal
    0.38
     DEAL
    0.36
     Deal
    0.34
    Deal
    0.33
    writing
    0.31
     concerns
    0.30
    Activations Density 0.010%

    No Known Activations