© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23969
    Prev
    Next
    INDEX
    Explanations

    street skating

    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
    åģķ
    -0.10
     Compass
    -0.09
    èĤ©èĨĢ
    -0.09
    çĸŁ
    -0.09
    æĭħ
    -0.09
    æŶåĢĻ
    -0.08
    æĺİ亮
    -0.08
    ä»»ä½ķæŶåĢĻ
    -0.08
    UFF
    -0.08
     loc
    -0.08
    POSITIVE LOGITS
    éħ·
    0.09
    稼
    0.09
     Aç
    0.09
    åĬ¨åĬĽ
    0.09
    .PREFERRED
    0.09
    ä¹³ä¸ļ
    0.08
    åı£åı·
    0.08
    æªĢ
    0.08
    è¸ħ
    0.08
    çĿ£åĬŀ
    0.08
    Activations Density 0.036%

    No Known Activations