© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7432
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    åĩºçİ°éĹ®é¢ĺ
    -0.11
    å¹²èĦĨ
    -0.10
    è¡©
    -0.09
    å¨ĥ
    -0.09
    æŀ«
    -0.09
    =Value
    -0.09
    ãģĨãģ¡ãģ«
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    uran
    -0.08
    æĢ»é¢Ŀ
    -0.08
    POSITIVE LOGITS
    oidal
    0.12
    styl
    0.09
    ensis
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    _OW
    0.08
    å®ı
    0.08
    ffects
    0.08
    æ¶ī
    0.08
    istor
    0.08
    aste
    0.08
    Activations Density 0.058%

    No Known Activations