© 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. 29414
    Prev
    Next
    INDEX
    Explanations

    influence

    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
    Not in Any Lists

    No Comments

    Negative Logits
     influencing
    -0.38
     influence
    -0.34
    å½±åĵįåĬĽ
    -0.32
     Influence
    -0.31
    çļĦå½±åĵį
    -0.31
     influ
    -0.30
     Influ
    -0.29
    alle
    -0.29
    å½±éŁ¿
    -0.28
    æĿIJ
    -0.27
    POSITIVE LOGITS
    è·Łä¸įä¸Ĭ
    0.31
    çĹĤ
    0.29
    lags
    0.28
    orges
    0.27
    ceeded
    0.26
    tober
    0.25
    ç¥ŀæĥħ
    0.25
     DISCLAIMER
    0.25
    æŃĮè¯į
    0.25
    å¾Ĺå¾Ī好
    0.25
    Activations Density 1.177%

    No Known Activations