© 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. 21040
    Prev
    Next
    INDEX
    Explanations

    luxury and comfort

    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
    ñ
    -0.10
    éĿ¢åŃĶ
    -0.09
    çĻ½å¤©
    -0.09
    ç»Ī究
    -0.09
    obl
    -0.09
    身ä¸Ĭ
    -0.08
    åĩºè®©
    -0.08
    è¡Į人
    -0.08
    åħīåѦ
    -0.08
    conte
    -0.08
    POSITIVE LOGITS
    èĪĴéĢĤ
    0.16
    享åıĹ
    0.16
    lux
    0.15
    çĶŁæ´»æ°´å¹³
    0.15
     lux
    0.15
    享
    0.15
    çĶŁæ´»è´¨éĩı
    0.14
    å¯Įè£ķ
    0.14
    奢åįİ
    0.14
    èĪĴæľį
    0.14
    Activations Density 0.079%

    No Known Activations