© 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. 36000
    Prev
    Next
    INDEX
    Explanations

    header files and reserved rights

    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
    åİĮ
    -0.10
    éķ¿ä¸īè§Ĵ
    -0.09
     Marty
    -0.08
    åĪ¶åº¦æĶ¹éĿ©
    -0.08
    afil
    -0.08
    æĤ´
    -0.08
    粪
    -0.08
    峨
    -0.08
    åŃ°
    -0.08
    nc
    -0.08
    POSITIVE LOGITS
    ä¸įåĬ¨äº§
    0.10
     UObject
    0.09
    æ¡Ħ
    0.09
    æĿĥåĪ©
    0.09
    å®Ļ
    0.09
    ehen
    0.09
    kaar
    0.09
    çĶŁçī©åѦ
    0.09
    èĩªæ²»åĮº
    0.09
    èĵĿåĽ¾
    0.09
    Activations Density 0.051%

    No Known Activations