© 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. 21941
    Prev
    Next
    INDEX
    Explanations

    's, is, 're, had, needs

    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£ĺ
    -0.09
    äºĶä¸Ģ
    -0.09
    è··
    -0.09
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.08
    _BITS
    -0.08
    åĪĽæĸ°åŀĭ
    -0.08
     mixer
    -0.08
    ãģ§ãģĻãģĹ
    -0.08
    åı¯ä»¥çľĭåĩº
    -0.08
    缶
    -0.08
    POSITIVE LOGITS
    çī¢
    0.09
    è¿Ļä¸ĢåĪĩ
    0.09
    æĪIJ为ä¸ĢåIJį
    0.08
    ä¸įå®Į
    0.08
    èĩ³åħ³
    0.08
    æł¹æľ¬æ²¡æľī
    0.08
     naked
    0.08
    æ³±
    0.08
    èĩ³åħ³éĩįè¦ģ
    0.08
    çļĦéĤ£ä¸Ģ
    0.08
    Activations Density 0.110%

    No Known Activations