© 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. 151144
    Prev
    Next
    INDEX
    Explanations

    health and drug use

    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
    Not in Any Lists

    No Comments

    Negative Logits
    为æĤ¨
    -0.28
    åħ»
    -0.26
    eware
    -0.25
     СовеÑĤ
    -0.24
    ä»Ķç»Ĩ
    -0.23
    åĽ½åľŁ
    -0.23
    "c
    -0.23
    -transparent
    -0.23
    ĽĦ
    -0.23
    æĤ¨çļĦ
    -0.23
    POSITIVE LOGITS
     fluor
    0.27
    累积
    0.27
    积累
    0.25
     accumulator
    0.25
     Blink
    0.25
    éĿĴå±±
    0.24
     alg
    0.24
    积èĵĦ
    0.24
    è¶ĬæĿ¥è¶Ĭ大
    0.24
     upscale
    0.23
    Activations Density 0.131%

    No Known Activations