© 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. 112069
    Prev
    Next
    INDEX
    Explanations

    function words

    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
    对æĪij们
    -0.37
    æĪij们çļĦ
    -0.32
    对æĪij
    -0.32
    ç»ĻæĪij们
    -0.28
     Dam
    -0.28
    ä»Ģ麽
    -0.28
     OUR
    -0.28
     our
    -0.27
    atch
    -0.27
     ours
    -0.27
    POSITIVE LOGITS
    geh
    0.27
    è¢Ĥ
    0.27
    idden
    0.26
    .Middle
    0.26
    ä¼ļ被
    0.25
    .appspot
    0.25
    å¸ĤåľºåĮĸ
    0.25
    itere
    0.25
    åħ¶æīĢ
    0.24
    è°¯
    0.24
    Activations Density 0.006%

    No Known Activations