© 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. 34736
    Prev
    Next
    INDEX
    Explanations

    interrogative words, punctuation, and conjunctions

    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
    æŶåħī
    -0.10
    è°Ł
    -0.09
    ergic
    -0.09
    éĶĢåĶ®æ¸łéģĵ
    -0.09
    adium
    -0.09
    èĭģ
    -0.09
    åĪ°åľº
    -0.09
    иÑĢов
    -0.09
    èݳ
    -0.09
    åĺīå¹´
    -0.09
    POSITIVE LOGITS
    ä¸Ģåı·
    0.09
     etc
    0.08
    人çī©
    0.08
    æł¡å¤ĸ
    0.08
    令
    0.08
    acon
    0.08
    caffold
    0.07
    sole
    0.07
    çŃīçŃī
    0.07
    è¡Įäºĭ
    0.07
    Activations Density 0.024%

    No Known Activations