© 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. 24-TRANSCODER-HP
    7. 149156
    Prev
    Next
    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åºĶçĶ¨äºİ
    -0.26
    å«Ĥ
    -0.26
     itself
    -0.26
    纳åħ¥
    -0.25
    ccoli
    -0.25
    çķĢ
    -0.24
    steen
    -0.23
    اء
    -0.23
    çļĦåºĶçĶ¨
    -0.23
    ç§ijçłĶéĻ¢æīĢ
    -0.23
    POSITIVE LOGITS
    ose
    0.33
    antal
    0.29
     Inventory
    0.29
    oose
    0.27
     examples
    0.27
    OSE
    0.26
     Kitt
    0.25
     Injectable
    0.25
    ãĤ¿ãĥ«
    0.25
    ÑģÑĥ
    0.24
    Activations Density 0.006%

    No Known Activations