© 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. 30-TRANSCODER-HP
    7. 95229
    Prev
    Next
    INDEX
    Explanations

    start of document

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OAD
    -0.29
    æijĶ
    -0.29
    ichi
    -0.28
    pir
    -0.27
    ycin
    -0.26
    oad
    -0.26
    pora
    -0.26
    åı·
    -0.26
    elsen
    -0.25
    ystone
    -0.25
    POSITIVE LOGITS
     finite
    0.32
    éĸ£
    0.31
    finite
    0.28
    _wo
    0.28
     Finite
    0.28
    æľ¬ä¹¦
    0.27
    Finite
    0.27
     зап
    0.27
    bib
    0.26
     book
    0.26
    Activations Density 0.883%

    No Known Activations