© 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. 9960
    Prev
    Next
    INDEX
    Explanations

    that ... in

    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
     Pars
    -0.08
     pob
    -0.08
    Deg
    -0.08
    没éĹ®é¢ĺ
    -0.08
     pigs
    -0.08
    eric
    -0.08
    ç¬ĶèĢħ
    -0.08
     pig
    -0.08
    æĹłçĸij
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
    POSITIVE LOGITS
    åĺĪ
    0.09
    年人
    0.09
    çĸ«
    0.09
    çªģåıij
    0.09
    å¹´ä¹ĭ
    0.09
    ä¹ŁçŁ¥éģĵ
    0.08
    éŃģ
    0.08
    è°µ
    0.08
    dess
    0.08
    è¿ľæĻ¯
    0.08
    Activations Density 0.046%

    No Known Activations