© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26245
    Prev
    Next
    INDEX
    Explanations

    degradable / dissolution

    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
    Negative Logits
    :focus
    -0.10
    waukee
    -0.09
    çľĭä»ĸ
    -0.09
    åĢ¦
    -0.09
    黩
    -0.08
     LC
    -0.08
    åIJįåĪĹ
    -0.08
    uis
    -0.08
    ç¿İ
    -0.08
    .inspect
    -0.08
    POSITIVE LOGITS
    ä¸įçķĻ
    0.10
     sacr
    0.10
    éĶĢæ¯ģ
    0.10
    æ¶Ī失
    0.09
     dissolve
    0.09
    æĭĨ
    0.09
    åŁķ
    0.09
     dissolution
    0.09
    uture
    0.09
    丢
    0.09
    Activations Density 0.178%

    No Known Activations