© 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. 50536
    Prev
    Next
    INDEX
    Explanations

    genus name suffix

    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
     yab
    -0.09
    æĸ¡
    -0.09
     Cherry
    -0.09
    æªŀ
    -0.09
    åĵģç§į
    -0.09
    æݺ
    -0.09
     Kı
    -0.09
    æłª
    -0.09
    åį¡æĭī
    -0.08
    çī§åľº
    -0.08
    POSITIVE LOGITS
    çĥŃè¡Ģ
    0.10
    Ñħо
    0.09
    uros
    0.09
    åķĨåĬ¡éĥ¨
    0.09
    好çİ©
    0.08
    åıĺæĢģ
    0.08
    examples
    0.08
    andex
    0.08
    ç±»
    0.08
     Prot
    0.08
    Activations Density 0.288%

    No Known Activations