© 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. 36880
    Prev
    Next
    INDEX
    Explanations

    psychiatric disorder

    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
    éĢĤ度
    -0.08
    zag
    -0.08
     Coding
    -0.08
    çĶŁæ´»çļĦ
    -0.08
    æģ¸
    -0.08
    spi
    -0.08
    åģ¶
    -0.08
     swe
    -0.08
    çIJIJ
    -0.08
    itos
    -0.08
    POSITIVE LOGITS
    ç²¾ç¥ŀçĹħ
    0.14
    çĻ«
    0.13
     madness
    0.12
    çĸ¯
    0.12
    çĺĭ
    0.12
    å¿ĥçIJĨåģ¥åº·
    0.11
     пÑģиÑħ
    0.11
     insanity
    0.10
    çļĦç²¾ç¥ŀ
    0.10
    ä¸įæ¸ħ
    0.10
    Activations Density 0.108%

    No Known Activations