© 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. 20-TRANSCODER-HP
    7. 64840
    Prev
    Next
    INDEX
    Explanations

    Computer-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æīĭä¸Ń
    -0.28
    çľģæķĻèĤ²åİħ
    -0.26
    侦
    -0.26
    mediately
    -0.25
    illions
    -0.24
     vielen
    -0.24
    æľīéĻIJ
    -0.24
     langs
    -0.24
     cazzo
    -0.24
    è¿Ļ段æŶéĹ´
    -0.24
    POSITIVE LOGITS
    Ĥ¬
    0.30
    оÑģÑĮ
    0.28
    erb
    0.27
    icopt
    0.27
    ering
    0.26
    ITHER
    0.26
    ered
    0.25
    umbs
    0.25
    ÃŃf
    0.25
    bracht
    0.24
    Activations Density 2.231%

    No Known Activations