© 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. 95039
    Prev
    Next
    INDEX
    Explanations

    quantitative

    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
    Negative Logits
    ringe
    -0.30
    opi
    -0.28
    _singular
    -0.26
     summar
    -0.26
    Abs
    -0.25
    rw
    -0.25
     ban
    -0.24
     bans
    -0.24
     Innoc
    -0.23
    _measurement
    -0.23
    POSITIVE LOGITS
    躯
    0.27
    ÑģоÑĤ
    0.26
    è¡¨æł¼
    0.26
    tables
    0.25
    æľºä½ĵ
    0.25
    éĶ¦
    0.25
    éĢļ车
    0.24
    身ä½ĵ
    0.24
    æĢ»è£ģ
    0.24
     alphabetical
    0.24
    Activations Density 0.002%

    No Known Activations