© 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. 63562
    Prev
    Next
    INDEX
    Explanations

    in addition

    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
     наÑĤÑĥÑĢалÑĮн
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    sofar
    -0.09
    ãģĨãģ¡ãģ«
    -0.09
    пÑĢод
    -0.09
    اÙĥ
    -0.09
    gether
    -0.08
     займ
    -0.08
    ofil
    -0.08
     ÑĢей
    -0.08
    POSITIVE LOGITS
    ä½ľçĶ¨
    0.10
    éĩįè¦ģ
    0.09
    ä¸Ģç§Ĵ
    0.09
    ä¸ĢåĪĢ
    0.09
    ivar
    0.08
    ç¬ij容
    0.08
    人çī©
    0.08
    çĶŁåij½
    0.08
    æłĩåĩĨ
    0.08
    AMA
    0.08
    Activations Density 0.099%

    No Known Activations