© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36604
    Prev
    Next
    INDEX
    Explanations

    define, enter, choose, options

    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
     Jahres
    -0.10
    chema
    -0.09
    Ñĥж
    -0.09
    جاÙħ
    -0.09
    걸
    -0.09
    езн
    -0.09
    å¹³åĿĩæ°´å¹³
    -0.08
     ìłijê·¼
    -0.08
     ÑģлÑĥÑĩаÑı
    -0.08
    columnName
    -0.08
    POSITIVE LOGITS
    éĢīæĭ©
    0.10
    å¡«åĨĻ
    0.09
    æĺ¯åIJ¦
    0.09
     choose
    0.09
    çĭIJçĭ¸
    0.08
    çļĦéĢīæĭ©
    0.08
    æīĢæıIJä¾Ľ
    0.08
    æ¡Ĩ
    0.08
    ç»Ļèĩªå·±
    0.08
    ç®Ģ
    0.08
    Activations Density 0.098%

    No Known Activations