© 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. 9-TRANSCODER-HP
    7. 30237
    Prev
    Next
    INDEX
    Explanations

    err

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    é¢Ĺç²Ĵ
    -0.27
    ixed
    -0.27
     candidates
    -0.26
    èĨı
    -0.25
    éĶ¹
    -0.25
    âĪļ
    -0.25
     Candidates
    -0.25
    æ¡ĵ
    -0.25
    esium
    -0.24
    æĬĢå¸Ī
    -0.24
    POSITIVE LOGITS
    eur
    0.25
    ItemImage
    0.25
    |int
    0.24
    秤
    0.24
    Cop
    0.24
    /cop
    0.24
    身é«ĺ
    0.24
    peech
    0.24
    便æĺ¯
    0.24
     Lie
    0.24
    Activations Density 1.613%

    No Known Activations