© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1882
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    ç²¾èĭ±
    -0.10
    _TUN
    -0.10
    å²Ĺ
    -0.10
    PIO
    -0.10
    æĿĵ
    -0.10
    å»ºè®¾é¡¹çĽ®
    -0.09
    çįł
    -0.09
    èĩªèº«çļĦ
    -0.09
    èĩªèº«
    -0.09
    Ñģоб
    -0.09
    POSITIVE LOGITS
    å¾ĹæĦı
    0.09
    aic
    0.09
    åħ¨ä½ĵ
    0.08
    æĪIJ
    0.08
     vX
    0.08
    /generated
    0.08
    大çļĦ
    0.08
     Helpful
    0.08
     breakout
    0.07
    deal
    0.07
    Activations Density 0.720%

    No Known Activations