© 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. 33291
    Prev
    Next
    INDEX
    Explanations

    eligibility, qualify, rules, protection, credits

    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
    æķ¢
    -0.11
    éĢĨè¡Į
    -0.10
    æ¿Ģèµ·
    -0.09
    æķĻèĤ²æķĻåѦ
    -0.08
    缼è¡Į
    -0.08
    æķ¬ä¸ļ
    -0.08
    Ļ¨
    -0.08
    ticker
    -0.08
    ä¸ĵ
    -0.08
    å½±
    -0.08
    POSITIVE LOGITS
    ä½İä¿Ŀ
    0.13
    è´«åĽ°
    0.11
    åħ¨å®¶
    0.10
    elig
    0.10
     Lafayette
    0.10
    æķijæµİ
    0.09
    建档ç«ĭåį¡
    0.09
    çĶ³è¯·
    0.09
    æł¸å®ŀ
    0.09
    æı´åĬ©
    0.09
    Activations Density 0.063%

    No Known Activations