© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52805
    Prev
    Next
    INDEX
    Explanations

    over there

    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
    åįģ足
    -0.10
    IBC
    -0.09
    åĿĮ
    -0.09
    pec
    -0.08
    åIJĮæŃ¥
    -0.08
    èĥ½è¾¾åĪ°
    -0.08
    ews
    -0.08
    åħ¬å¼Ģ课
    -0.08
    æĦ¦
    -0.08
    ä¸įåı¯
    -0.08
    POSITIVE LOGITS
    åľ¨éĤ£éĩĮ
    0.36
    éĤ£éĩĮ
    0.34
    åľ¨è¿ĻéĩĮ
    0.28
    è¿ĻéĩĮ
    0.26
     here
    0.25
     ÑĤам
    0.25
    éĤ£åĦ¿
    0.25
     здеÑģÑĮ
    0.21
    è¿ĻéĩĮæľī
    0.21
    ãģĿãģĵãģ«
    0.20
    Activations Density 0.200%

    No Known Activations