© 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. 149396
    Prev
    Next
    INDEX
    Explanations

    Body detox/purification

    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
    unte
    -0.27
    åĮª
    -0.27
    SF
    -0.25
    XF
    -0.25
    æłĿ
    -0.24
    è¡£
    -0.24
    社
    -0.24
     Greatest
    -0.23
    ç©Ĺ
    -0.23
     Commod
    -0.23
    POSITIVE LOGITS
    èĤ¾èĦı
    0.35
     kidneys
    0.33
    èĤłèĥĥ
    0.29
    èĿĮ
    0.29
     internal
    0.29
    ifen
    0.28
    çģµéŃĤ
    0.28
     Keller
    0.28
    çļĦçģµéŃĤ
    0.27
     kidney
    0.27
    Activations Density 0.110%

    No Known Activations