© 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. 51530
    Prev
    Next
    INDEX
    Explanations

    autocomplete or completion

    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
    _HIT
    -0.09
    尾巴
    -0.08
    ä¸įå®ļ
    -0.08
     sposób
    -0.08
    rez
    -0.08
     Tro
    -0.08
    izzle
    -0.08
    åĪ°ä½į
    -0.08
    èµ°å»Ĭ
    -0.08
    ä¼łéĢģ
    -0.08
    POSITIVE LOGITS
    æĹ¶æ®µ
    0.09
     ldc
    0.09
    åĨ¶éĩij
    0.09
    iliar
    0.09
     XT
    0.09
    ä¸Ģ段
    0.08
    ä¸Ģç»Ħ
    0.08
    æ¸ħåĩī
    0.08
    éģ®
    0.08
    åĽ½åĨħå¸Ĥåľº
    0.08
    Activations Density 0.002%

    No Known Activations