© 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. 10482
    Prev
    Next
    INDEX
    Explanations

    are all together

    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
    åĽ¢
    -0.08
    èĮĹ
    -0.08
    éĵ¢
    -0.08
    ä¼łåĩº
    -0.08
     male
    -0.08
     overt
    -0.08
    yme
    -0.08
     spare
    -0.08
     Male
    -0.08
    åİĦ
    -0.08
    POSITIVE LOGITS
    åħ±åIJĮ
    0.11
    åħ±åIJĮä½ĵ
    0.10
    ä¸Ģä½ĵ
    0.10
    åĴİ
    0.10
    åij½è¿IJ
    0.10
    å½¼æѤ
    0.09
    æģ¯æģ¯
    0.09
    èµĦæºIJåħ±äº«
    0.09
    åĩºåľº
    0.09
    ATORY
    0.09
    Activations Density 0.061%

    No Known Activations