© 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. 63249
    Prev
    Next
    INDEX
    Explanations

    plus sign followed by quantity

    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
    æĹ©æĻļ
    -0.11
    æį»
    -0.09
    éļ¼
    -0.09
    TES
    -0.08
    oud
    -0.08
    çĵľ
    -0.08
    otherwise
    -0.08
    æ£Ģ
    -0.08
    åIJİåĭ¤
    -0.08
    uld
    -0.08
    POSITIVE LOGITS
    unto
    0.10
    æŬ
    0.09
    nova
    0.09
    åĩĨç¡®
    0.09
    hin
    0.08
    baugh
    0.08
    accur
    0.08
    çļĦæŶéĹ´éĩĮ
    0.08
    åĩĨ
    0.08
    å¢ħ
    0.08
    Activations Density 0.017%

    No Known Activations