© 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. 96789
    Prev
    Next
    INDEX
    Explanations

    would

    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
     giving
    -1.30
     give
    -1.25
    ç»Ļ
    -1.20
     gives
    -1.18
    ç»ĻäºĪ
    -1.17
     Give
    -1.16
    give
    -1.16
    Give
    -1.12
     Giving
    -1.12
    ç»ĻäºĨ
    -1.10
    POSITIVE LOGITS
     having
    0.32
    Having
    0.29
     avere
    0.27
    having
    0.27
     Having
    0.26
     avoir
    0.25
    è°´
    0.25
    è¾Ī
    0.24
    ATO
    0.24
    æľīäºĨ
    0.24
    Activations Density 0.905%

    No Known Activations