© 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. 129415
    Prev
    Next
    INDEX
    Explanations

    computer-generated texts

    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
    ccione
    -0.30
    å²ģæŶ
    -0.25
    []{"
    -0.24
    é¢ĦèѦ
    -0.23
    æĸ°æ¨¡å¼ı
    -0.23
    ä¸Ģ件äºĭæĥħ
    -0.23
    æŀģèĩ´
    -0.23
    lec
    -0.23
    éĿ©
    -0.23
     vagy
    -0.23
    POSITIVE LOGITS
     setName
    0.28
    anga
    0.27
    Translations
    0.26
    .deg
    0.26
    .synthetic
    0.25
    åIJį称
    0.25
    endra
    0.25
    Lost
    0.25
    stra
    0.24
    inders
    0.24
    Activations Density 4.474%

    No Known Activations