© 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. 30126
    Prev
    Next
    INDEX
    Explanations

    rous ive selective ivity

    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
    аÑĨион
    -0.31
    atron
    -0.30
    è´¢æĶ¿éĥ¨
    -0.28
    Ñģкоп
    -0.27
    åĬł
    -0.27
    oS
    -0.26
     sıkıntı
    -0.26
    atorial
    -0.26
    åĴĮæĬĢæľ¯
    -0.25
    é£İæļ´
    -0.25
    POSITIVE LOGITS
    phalt
    0.27
    sı
    0.26
     dvd
    0.26
    åĪĨ离
    0.26
    ÂŃtion
    0.26
     centres
    0.25
    RITE
    0.25
     unst
    0.25
     ess
    0.25
     DVD
    0.25
    Activations Density 1.506%

    No Known Activations