© 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. 62971
    Prev
    Next
    INDEX
    Explanations

    Technical support questions

    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
    é¡¿
    -0.27
    çĿ¢
    -0.24
    æĪĪ
    -0.24
    rab
    -0.24
    çīµ
    -0.23
     ni
    -0.23
    LowerCase
    -0.23
     led
    -0.23
    arem
    -0.23
     illuminated
    -0.23
    POSITIVE LOGITS
    å¢Ģ
    0.29
    (_,
    0.28
    ewise
    0.28
    dale
    0.25
    loor
    0.25
     tablename
    0.24
    beat
    0.24
    .tex
    0.24
    çĽ¡
    0.24
    orest
    0.24
    Activations Density 26.538%

    No Known Activations