© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36582
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    -alone
    -0.09
    èį¡
    -0.08
    å¤ļæķ°
    -0.08
    áĢĬ
    -0.07
    emic
    -0.07
     Slot
    -0.07
     eq
    -0.07
    ä»ĸ们ä¼ļ
    -0.07
    rift
    -0.07
    _slot
    -0.07
    POSITIVE LOGITS
    è¿Ļ个éĹ®é¢ĺ
    0.16
    èĭ¦æģ¼
    0.13
    è¿ĻäºĽéĹ®é¢ĺ
    0.11
    请æķĻ
    0.11
    çĦ¦æĢ¥
    0.11
    ä¸ĭéĿ¢å°±
    0.10
    äºŁ
    0.10
    骥
    0.10
    çIJ
    0.10
    寻æ±Ĥ
    0.10
    Activations Density 0.259%

    No Known Activations