© 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. 17773
    Prev
    Next
    INDEX
    Explanations

    inhibition and stimulation

    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
    æħ£
    -0.10
    æĹłæīĢè°ĵ
    -0.10
    æĥ¯
    -0.10
    RID
    -0.09
    å¿į
    -0.09
    翼
    -0.08
    dag
    -0.08
    ëĭ«
    -0.08
     ÑĪиÑĢоко
    -0.08
     perhaps
    -0.08
    POSITIVE LOGITS
     hint
    0.09
    çļĦæķĪæŀľ
    0.09
    åªĴ
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    å®ŀéªĮ
    0.08
    æķĪæŀľ
    0.08
    å½ĵåį³
    0.08
    åĶĨ
    0.08
    å¾Īæ¼Ĥ亮
    0.08
    æī®
    0.08
    Activations Density 2.225%

    No Known Activations