© 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. 29136
    Prev
    Next
    INDEX
    Explanations

    le

    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
    ä¸Ģåı£
    -0.32
    ationally
    -0.31
    èĩªåĬ©
    -0.28
    çĵĺ
    -0.28
    athe
    -0.26
     keyed
    -0.25
    æ¬
    -0.25
    uary
    -0.25
    人æ°ijåĮ»éĻ¢
    -0.25
    梯
    -0.24
    POSITIVE LOGITS
    ASI
    0.27
    (compact
    0.25
     Judaism
    0.25
    <translation
    0.25
    รา
    0.25
     purch
    0.24
     Dani
    0.24
     Twe
    0.24
    çģ¿
    0.24
    или
    0.24
    Activations Density 3.081%

    No Known Activations