© 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. 95207
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     erv
    -0.26
    ÑĢÑĥÑĩ
    -0.24
     EPS
    -0.24
     commander
    -0.23
    _secs
    -0.23
    SWG
    -0.23
     Hum
    -0.23
     ep
    -0.23
     defaultMessage
    -0.23
    epam
    -0.23
    POSITIVE LOGITS
    ound
    0.33
    agger
    0.33
    sky
    0.30
    åįĹæµ·
    0.28
    æłĩ
    0.28
    å¾Ĺ天
    0.27
    æĮ¯
    0.27
    old
    0.27
    agic
    0.27
    ically
    0.26
    Activations Density 0.828%

    No Known Activations