© 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. 35950
    Prev
    Next
    INDEX
    Explanations

    fighting events and results

    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
    åºĩ
    -0.09
    ONGL
    -0.09
    ATER
    -0.08
     rebate
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
    .synthetic
    -0.08
    ienie
    -0.08
    ç»Ĵ
    -0.08
    Clusters
    -0.08
    ç§ĺ
    -0.08
    POSITIVE LOGITS
    ä½ĵéĩį
    0.10
    KO
    0.10
    æijĶ
    0.09
    éĢīæīĭ
    0.09
    arena
    0.09
    伤çĹħ
    0.09
    ç»ı纪人
    0.09
     KO
    0.09
    ç»ı纪
    0.09
    æŃ¦æľ¯
    0.08
    Activations Density 0.149%

    No Known Activations