© 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. 32027
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    liqu
    -0.11
    LEncoder
    -0.11
    .RunWith
    -0.10
    	TokenName
    -0.10
    ä½ıåĿĢ
    -0.10
    太ä¹ħ
    -0.10
    ++.
    -0.10
    ä¸ĭåįĬ
    -0.10
    .spi
    -0.10
    çĸĥ
    -0.09
    POSITIVE LOGITS
    æ§Ľ
    0.09
    以åıĬ
    0.08
     most
    0.08
    åİ»éĻ¤
    0.07
    maf
    0.07
    ä¹Łå°±æĺ¯
    0.07
     d
    0.07
     PO
    0.07
    ç«ŀ
    0.07
    /how
    0.07
    Activations Density 0.218%

    No Known Activations