© 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. 11581
    Prev
    Next
    INDEX
    Explanations

    giving away or offering

    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
    åħ¸åŀĭçļĦ
    -0.09
    åIJİéĿ¢çļĦ
    -0.09
    æ©ĺ
    -0.09
    á¿Ĩ
    -0.09
    _GC
    -0.08
    éĢ¼
    -0.08
    éĢ®
    -0.08
    寿
    -0.08
    ή
    -0.08
    åĪº
    -0.08
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.11
    ä¿¡ä»»
    0.10
    æļ´éľ²
    0.10
    çļĦä¿¡ä»»
    0.09
    èĢĻ
    0.09
    èĩªå·±
    0.09
    åľ°è²Į
    0.09
    åİĺ
    0.09
    æīĵ好
    0.09
    æķŀ
    0.09
    Activations Density 0.062%

    No Known Activations