© 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. 7288
    Prev
    Next
    INDEX
    Explanations

    lists of actions

    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
    ä¹ŁåĽłæѤ
    -0.10
     kenn
    -0.10
    åĴĮ个人
    -0.09
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.09
    è¿ĽèĢĮ
    -0.09
    社ä¼ļ稳å®ļ
    -0.09
    ä¹ĥèĩ³
    -0.09
    çĶļèĩ³
    -0.09
    èĢ½
    -0.09
    æľ¬åľ°
    -0.09
    POSITIVE LOGITS
     either
    0.09
    è¦ģä¹Ī
    0.08
    åħ¨å¤©
    0.08
     eÄŁer
    0.08
     Marcos
    0.08
    éĤ£æ®µ
    0.08
    æŀ¶
    0.07
    åıªè¦ģæĺ¯
    0.07
    æĮ
    0.07
     map
    0.07
    Activations Density 0.169%

    No Known Activations