© 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. 32-TRANSCODER-HP
    7. 42972
    Prev
    Next
    INDEX
    Explanations

    code, foreign language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kh
    -0.38
     Moscow
    -0.36
    èİ«æĸ¯ç§ij
    -0.34
    akh
    -0.32
     Ts
    -0.32
     ts
    -0.31
    tsy
    -0.30
    Zh
    -0.30
    Ts
    -0.29
    ny
    -0.28
    POSITIVE LOGITS
    iola
    0.30
    人人
    0.29
     Civ
    0.26
     genu
    0.24
    ãĥ¼ãĤ¹
    0.24
     defaultProps
    0.24
    éļ§
    0.24
     Wax
    0.23
    ettes
    0.23
    åĽŀ头çľĭ
    0.23
    Activations Density 0.008%

    No Known Activations