© 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. 33-TRANSCODER-HP
    7. 54487
    Prev
    Next
    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aleb
    -0.25
    ulations
    -0.24
    è··
    -0.24
    ØŃØ©
    -0.23
    å²ĺ
    -0.23
    NEY
    -0.23
    课é¢ĺ
    -0.23
    enez
    -0.23
    æ¼¢
    -0.23
    æ±ī
    -0.23
    POSITIVE LOGITS
     id
    0.93
    id
    0.86
     Id
    0.85
    -id
    0.84
    _id
    0.83
     ids
    0.82
    ids
    0.82
    Id
    0.79
    .id
    0.78
     ID
    0.77
    Activations Density 0.009%

    No Known Activations