© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26527
    Prev
    Next
    INDEX
    Explanations

    non-English words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ŁåĽłæѤ
    -0.12
    å®ĥ们
    -0.11
    éĻ¤æѤ
    -0.10
    对ä»ĸ们
    -0.10
    çĩĶ
    -0.10
    ä½ľåĵģåĨħ容
    -0.10
    æīĢæľīæĥħèĬĤ
    -0.10
    æīĢ以ä»ĸ
    -0.10
    éĥĽ
    -0.10
    æīĢ带æĿ¥çļĦ
    -0.10
    POSITIVE LOGITS
    oso
    0.08
    $$$
    0.07
    icro
    0.07
    çļĩåĨł
    0.07
    angi
    0.07
    iy
    0.07
    ä¸Ĭå¹´
    0.07
    ä¸Ĭæ¦ľ
    0.06
     Hugo
    0.06
    çĶ¨
    0.06
    Activations Density 0.070%

    No Known Activations