© 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. 5501
    Prev
    Next
    INDEX
    Explanations

    make the most of

    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
     sph
    -0.10
    åı¯ä»¥çĽ´æİ¥
    -0.09
    ataka
    -0.09
    å¨Ł
    -0.08
    çī¹ç§į
    -0.08
    æīĴ
    -0.08
    éĤł
    -0.08
    ä¸Ģå¹ķ
    -0.08
    大家ä¸Ģèµ·
    -0.08
    好åĿı
    -0.08
    POSITIVE LOGITS
    åĪ©çĶ¨çİĩ
    0.11
    æľīéĻIJ
    0.11
    æ½ľèĥ½
    0.11
    æīĭä¸ŃçļĦ
    0.11
    èµĦæºIJä¼ĺåĬ¿
    0.11
    å®Ŀè´µ
    0.10
    å®Ŀè´µçļĦ
    0.10
    åıijæĮ¥
    0.10
    IMO
    0.10
    çİ°æľī
    0.09
    Activations Density 0.079%

    No Known Activations