© 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. 3766
    Prev
    Next
    INDEX
    Explanations

    website URLs and technical links

    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
    èIJ¥éĢłèī¯å¥½
    -0.09
    座ä½į
    -0.08
    lbrace
    -0.08
    æ¿ij
    -0.08
    滩
    -0.08
     Disclosure
    -0.08
    ä¸ī级
    -0.08
    çķĻä½ı
    -0.08
    亲
    -0.08
    æĭĽåij¼
    -0.08
    POSITIVE LOGITS
    æĹĭ
    0.11
    æĪijè¿ĺæĺ¯
    0.10
    åĬĽè¿ĺæĺ¯
    0.10
    Lon
    0.09
    eer
    0.09
    å·¥ä½ľä»»åĬ¡
    0.09
    epy
    0.09
    èĢ»
    0.09
    åħ¨èĥ½
    0.09
    éĢ¼è¿ij
    0.08
    Activations Density 0.002%

    No Known Activations