© 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. 12168
    Prev
    Next
    INDEX
    Explanations

    cannot deny or object

    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
    ảo
    -0.09
    æĤħ
    -0.09
    åĩłä¹İæīĢæľī
    -0.09
     Rodrigo
    -0.09
     Roe
    -0.08
    èĪ·
    -0.08
     Cla
    -0.08
    ona
    -0.08
    ç¹ĩ
    -0.08
     меÑĢ
    -0.08
    POSITIVE LOGITS
    çݰ代åĨľä¸ļ
    0.10
    anything
    0.10
    PIN
    0.10
    çIJ¥
    0.09
    海绵
    0.09
    åĵªæĢķ
    0.09
    ény
    0.09
    太ä¹ħ
    0.09
    ãģķãģĪ
    0.09
    æľīä»»ä½ķ
    0.09
    Activations Density 0.034%

    No Known Activations