© 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. 29287
    Prev
    Next
    INDEX
    Explanations

    radiation levels/measurements

    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
     adaptable
    -0.29
    ck
    -0.28
    äº
    -0.26
    bac
    -0.26
    OMIC
    -0.26
    cks
    -0.26
    åįļ士åѦä½į
    -0.25
    esian
    -0.25
    æ²ī
    -0.25
    cow
    -0.24
    POSITIVE LOGITS
     Hayden
    0.29
    inery
    0.27
    éĭª
    0.27
    ä»İ严
    0.26
    éĵº
    0.26
    èĢĻ
    0.26
    chemes
    0.25
    è¿ĻçĤ¹
    0.25
    罩
    0.24
    ÑĢев
    0.24
    Activations Density 3.381%

    No Known Activations