© 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. 108164
    Prev
    Next
    INDEX
    Explanations

    Data structures or arrangements

    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
    æĪ·
    -0.30
    åİļéĩį
    -0.28
    ì¹Ń
    -0.27
     Còn
    -0.26
    ammer
    -0.25
    shi
    -0.25
    -profit
    -0.24
    zá
    -0.24
    yg
    -0.23
    Ñĩив
    -0.23
    POSITIVE LOGITS
    ble
    0.26
    æĿ¥è¿Ľè¡Į
    0.24
    æģ¶
    0.24
     inline
    0.24
    azel
    0.24
     behaviours
    0.23
     exclusion
    0.23
    ä¸įä¿¡
    0.23
    ettle
    0.23
    inline
    0.23
    Activations Density 1.541%

    No Known Activations