© 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. 141977
    Prev
    Next
    INDEX
    Explanations

    computer code/technical data

    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
    æ°¸è¿ľä¸įä¼ļ
    -0.27
     eccentric
    -0.26
     humili
    -0.26
     çift
    -0.25
    anghai
    -0.25
    ecc
    -0.25
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.24
    elastic
    -0.24
    çľĭæĿ¥
    -0.24
    éļ¾å¾Ĺ
    -0.24
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.30
    /exp
    0.27
     fuel
    0.26
    åħ¶æīĢ
    0.25
    оÑģÑĤ
    0.25
    osa
    0.25
    osas
    0.24
    udio
    0.24
     fds
    0.24
    wers
    0.24
    Activations Density 16.146%

    No Known Activations