© 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. 32624
    Prev
    Next
    INDEX
    Explanations

    not an expert

    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
    æĹłäºº
    -0.09
    纯åĩĢ
    -0.08
     Nr
    -0.08
     misc
    -0.08
    å±¥èģĮ
    -0.08
    æ·³
    -0.08
    à¸ŀา
    -0.08
     cra
    -0.08
    åľ¨æİ¥åıĹ
    -0.08
    stamp
    -0.08
    POSITIVE LOGITS
    ä¸ĵ家åѦèĢħ
    0.12
    ä¸ĵ家
    0.11
    åŁŃ
    0.10
    ä½ĨæĪij
    0.10
    奢ä¾Ī
    0.10
    expert
    0.09
    ä½Ĩæĺ¯æĪij
    0.09
     Expert
    0.09
    å°Ī家
    0.09
    ponents
    0.09
    Activations Density 0.235%

    No Known Activations