© 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. 16708
    Prev
    Next
    INDEX
    Explanations

    sniffing and smelling

    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
    Negative Logits
    нак
    -0.10
    itsu
    -0.09
    ç¥ĵ
    -0.09
     ÑģмÑĭÑģл
    -0.09
    à¤ł
    -0.08
    MENT
    -0.08
     ÑģÑĢеди
    -0.08
    ement
    -0.08
    GetObject
    -0.08
    å½»åºķ
    -0.08
    POSITIVE LOGITS
    åĹħ
    0.12
    çĨı
    0.11
    çłĶ究æīĢ
    0.10
    æİīäºĨ
    0.10
    .sky
    0.10
    æĸ¯åĿ¦
    0.09
     sniff
    0.09
    enis
    0.09
    uze
    0.09
    çĭIJ
    0.09
    Activations Density 0.011%

    No Known Activations