© 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. 88140
    Prev
    Next
    INDEX
    Explanations

    More

    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
    é¦ĸä½į
    -0.28
    æľĢè¿ij
    -0.28
     best
    -0.27
     frequently
    -0.27
     last
    -0.26
    è¿ijæľŁ
    -0.26
    arest
    -0.26
     recently
    -0.26
    æľ«
    -0.26
    onto
    -0.25
    POSITIVE LOGITS
    >Main
    0.27
    åIJĥè¿ĩ
    0.26
    ooky
    0.26
    alted
    0.24
    idding
    0.24
    ä¸ĥ个
    0.24
    åľ¨ç½ij绾
    0.24
    èĿ´èĿ¶
    0.24
    Attrs
    0.23
    .fixed
    0.23
    Activations Density 0.016%

    No Known Activations