© 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. 22576
    Prev
    Next
    INDEX
    Explanations

    Santa and place names

    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¿ľæ´ĭ
    -0.12
    enga
    -0.10
    å¤ĸ交éĥ¨
    -0.10
    åľĪåŃIJ
    -0.09
    éĢļçŁ¥ä¹¦
    -0.09
    idel
    -0.09
    æŀģé«ĺ
    -0.09
    за
    -0.09
    _CONTINUE
    -0.09
    fromJson
    -0.09
    POSITIVE LOGITS
    å¸ĥ
    0.09
    亲èĩª
    0.08
    tera
    0.08
    çĶ¨è½¦
    0.07
    å¢ŀ
    0.07
     habil
    0.07
    ðŁı»
    0.07
    ruk
    0.07
    认è¯Ĩ
    0.07
    oras
    0.07
    Activations Density 0.002%

    No Known Activations