© 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. 21614
    Prev
    Next
    INDEX
    Explanations

    free download full version

    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
    æĹłå½¢
    -0.10
    ç³Ł
    -0.10
    æµģåŁŁ
    -0.09
    éĹ°
    -0.09
    æIJĶ
    -0.08
    çĵľ
    -0.08
    ä½ľæ¡Ī
    -0.08
    æĹłåĬĽ
    -0.08
    legg
    -0.08
    ëıħ
    -0.08
    POSITIVE LOGITS
    综
    0.09
    äºĽ
    0.09
     Nurs
    0.09
    æĮ¯å¥ĭ
    0.08
    ÙĩÙī
    0.08
    uur
    0.08
    æĢ§è´¨
    0.08
     ÑģоÑĨиалÑĮно
    0.08
     Stam
    0.08
    æŶéĹ´åĨħ
    0.08
    Activations Density 0.030%

    No Known Activations