© 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. 12429
    Prev
    Next
    INDEX
    Explanations

    it's a/an [adjective]

    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
    è·Ĺ
    -0.10
    rid
    -0.09
    ר
    -0.08
    RTC
    -0.08
    ç¤ģ
    -0.08
    çĽĹ
    -0.08
    æijĪ
    -0.08
    ÙħÙĬÙĨ
    -0.08
    çļĦæľĢåIJİä¸Ģ
    -0.08
    å°ıç»Ħ
    -0.08
    POSITIVE LOGITS
    çĿĽ
    0.10
     Packs
    0.09
    _iff
    0.09
    olate
    0.09
    اØ
    0.09
    /format
    0.09
    ifle
    0.08
    幡
    0.08
    åĺ¶
    0.08
    åĿİ
    0.08
    Activations Density 0.038%

    No Known Activations