© 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. 9078
    Prev
    Next
    INDEX
    Explanations

    is it ok

    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
    éĽĢ
    -0.10
    转移åĪ°
    -0.09
    é»Ħéĩij
    -0.09
    å»Ĭ
    -0.08
     há»ĵi
    -0.08
     Beaut
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    æŃ£å¥½
    -0.08
     kuk
    -0.08
    osal
    -0.08
    POSITIVE LOGITS
    çķħ
    0.08
    æīĢåľ¨
    0.08
    va
    0.08
    æ¸İ
    0.08
    éªĸ
    0.08
    æĽ
    0.08
    åIJĥ
    0.08
     ÙĨÙĤ
    0.08
    icer
    0.08
     spir
    0.08
    Activations Density 0.171%

    No Known Activations