© 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. 49687
    Prev
    Next
    INDEX
    Explanations

    community and local area

    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
    è§Ħ
    -0.09
    éĺŁä¼į
    -0.09
    æ¸ħåĩī
    -0.08
    æ¡¢
    -0.08
    è§ĦåĪĻ
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.08
     equip
    -0.08
    åįĥéĩĮ
    -0.08
    å¾ĹçĽĬ
    -0.08
    祯
    -0.08
    POSITIVE LOGITS
    社åĮº
    0.18
     community
    0.17
     communities
    0.16
    社åįĢ
    0.16
    åij¨åĽ´
    0.16
    åij¨è¾¹
    0.14
    åij¨åĽ´çļĦ
    0.14
    å½ĵåľ°äºº
    0.14
    Community
    0.13
    -community
    0.13
    Activations Density 0.113%

    No Known Activations