© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21448
    Prev
    Next
    INDEX
    Explanations

    Yii framework code

    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
     Belfast
    -0.10
    é»Ķ
    -0.10
    è´µå·ŀ
    -0.09
    è´µéĺ³
    -0.09
    _UNICODE
    -0.09
     Scotland
    -0.09
    æīĵåĩº
    -0.08
    éļĹ
    -0.08
    æĪIJéĥ½
    -0.08
    ä¸įçĪ±
    -0.08
    POSITIVE LOGITS
    婺
    0.10
    ç½ķ
    0.10
    åłĻ
    0.10
    æ±Ĺ
    0.10
     Ston
    0.09
    åĩºæ±Ĺ
    0.09
    严ç¦ģ
    0.09
    LOY
    0.09
    ç»ıèIJ¥çIJĨ念
    0.09
    æ²ģ
    0.09
    Activations Density 0.125%

    No Known Activations