© 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. 44002
    Prev
    Next
    INDEX
    Explanations

    repair

    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
    anic
    -0.29
    .nd
    -0.27
    ed
    -0.27
    沿çĿĢ
    -0.27
     Dane
    -0.26
    ILER
    -0.26
    å¾Ģä¸Ĭ
    -0.25
    (nd
    -0.25
    ancellationToken
    -0.24
    ihat
    -0.24
    POSITIVE LOGITS
     fixed
    0.47
    fixed
    0.45
    åĽºå®ļ
    0.44
     fix
    0.44
     fixes
    0.43
    Fixed
    0.41
     fixing
    0.41
    fix
    0.40
     Fix
    0.40
    .fix
    0.40
    Activations Density 0.005%

    No Known Activations