© 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. 34853
    Prev
    Next
    INDEX
    Explanations

    catalog year or course information

    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
    æĢĨ
    -0.09
    èĢ¿
    -0.09
    åħ¨èĥ½
    -0.09
    建档
    -0.09
     merg
    -0.09
    æ¬łç¼º
    -0.08
    åıijå±ķæł¼å±Ģ
    -0.08
    èĤĦ
    -0.08
    æ¯ķä¸ļçĶŁ
    -0.08
    lox
    -0.08
    POSITIVE LOGITS
    åĪij
    0.10
    ç»Ļèĩªå·±
    0.08
    çľī
    0.08
    íĥľ
    0.08
    AndGet
    0.08
    饶
    0.08
    ç¿İ
    0.08
    è¡Į驶
    0.08
    èĬĤåģĩæĹ¥
    0.08
     Ta
    0.08
    Activations Density 0.054%

    No Known Activations