© 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. 10829
    Prev
    Next
    INDEX
    Explanations

    idiopathic

    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
    峡
    -0.10
    峪
    -0.09
     Barg
    -0.09
    æĢ¥äºİ
    -0.09
    æŃ¥æŃ¥
    -0.09
    æµĨ
    -0.08
    å¾ĢåIJİ
    -0.08
    _extended
    -0.08
    éĹ´æİ¥
    -0.08
     SLOT
    -0.08
    POSITIVE LOGITS
    æĹłç¼ĺ
    0.20
    纯粹
    0.16
    纯
    0.14
    èİ«åIJįåħ¶å¦Ļ
    0.14
    èİ«åIJį
    0.13
     purely
    0.12
    ç´Ķ
    0.12
    çĻ½çĻ½
    0.12
    åĩŃ
    0.12
    毫æĹł
    0.12
    Activations Density 0.195%

    No Known Activations