© 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. 22-TRANSCODER-HP
    7. 87578
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ckett
    -0.26
    åį³ä¾¿
    -0.25
    asje
    -0.25
    owy
    -0.25
    ledon
    -0.24
     Shirt
    -0.23
    åį³ä½¿
    -0.23
    ä¹Łæ²¡
    -0.23
    ago
    -0.23
    uppen
    -0.23
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.27
     disap
    0.26
    é¦ĸåĪĽ
    0.25
    çļĦæĸ¹å¼ıæĿ¥
    0.25
    eteria
    0.25
    èľľ
    0.25
    æĺ¯éĿŀ
    0.25
    veys
    0.24
    distributed
    0.24
    vier
    0.24
    Activations Density 0.012%

    No Known Activations