© 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. 33-TRANSCODER-HP
    7. 52661
    Prev
    Next
    INDEX
    Explanations

    panic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ei
    -0.28
    yme
    -0.28
    ez
    -0.26
    shelf
    -0.25
    cat
    -0.25
    对æĪijæĿ¥è¯´
    -0.24
    eyer
    -0.24
    pkg
    -0.24
    ot
    -0.24
    tica
    -0.24
    POSITIVE LOGITS
    å°½
    0.26
    agara
    0.26
     controls
    0.25
     induced
    0.25
    åľ¨å¹¿å·ŀ
    0.24
    æĦĪ
    0.24
    诱导
    0.24
    æĢ§
    0.24
    æݧåĪ¶ç³»ç»Ł
    0.24
    çªģçł´
    0.24
    Activations Density 0.008%

    No Known Activations