© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 872
    Prev
    Next
    INDEX
    Explanations

    ethics review board approval

    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
    åı¬åĽŀ
    -0.08
    uur
    -0.08
    é¢ĦçķĻ
    -0.08
    ADR
    -0.08
     devil
    -0.08
    çķĻä¸ĭ
    -0.08
    çĪª
    -0.08
    è¿Ķ
    -0.07
    ç´łè´¨æķĻèĤ²
    -0.07
    aje
    -0.07
    POSITIVE LOGITS
    伤害
    0.11
    éĩįè¦ģåĨħ容
    0.11
    人ä½ĵ
    0.11
    é¢ģ
    0.10
    çļij
    0.10
    æŁľåı°
    0.10
    ç°Į
    0.10
    éħ¢
    0.09
    å°ıå¾®
    0.09
    åĨľçī§
    0.09
    Activations Density 0.085%

    No Known Activations