© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130483
    Prev
    Next
    INDEX
    Explanations

    management and organization

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ulos
    -0.31
    anka
    -0.28
    å½¼
    -0.27
     habit
    -0.25
     Nil
    -0.25
     mont
    -0.24
    pace
    -0.24
    项
    -0.24
    stead
    -0.24
    æīŃ转
    -0.24
    POSITIVE LOGITS
     breathe
    0.26
    tero
    0.26
    æĭĽæłĩ
    0.25
    æĺ¯åIJ¦ä¼ļ
    0.25
     migr
    0.24
    Mixin
    0.24
    ially
    0.24
    è±ĩ
    0.23
    ãģĻãĤĭãģ®ãģ¯
    0.23
    åŃ£åIJİ
    0.23
    Activations Density 12.378%

    No Known Activations