© 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. 20-TRANSCODER-HP
    7. 108403
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adows
    -0.30
    apan
    -0.29
    æħİ
    -0.26
    æĹĹ
    -0.26
    åľ°ä½į
    -0.24
    aday
    -0.24
    åģļ人
    -0.24
    aned
    -0.24
    aber
    -0.24
    club
    -0.24
    POSITIVE LOGITS
    åı¯è§Ĥ
    0.28
    æĢ¦
    0.25
    üm
    0.25
    ponents
    0.25
    æłĮ
    0.24
     beat
    0.24
     Regents
    0.23
    åħħå®ŀ
    0.23
    ä¸įæľį
    0.23
    ä¸Ĭä¸ĭ
    0.23
    Activations Density 39.478%

    No Known Activations