© 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. 37836
    Prev
    Next
    INDEX
    Explanations

    Vatican information

    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
    çķ¶æĤ¨åľ¨
    -0.10
    åŁĴ
    -0.09
    æ¦ĸ
    -0.09
    æĽ©
    -0.09
    ä¸į论æĺ¯
    -0.09
    èģĶæĥ³
    -0.09
    å°±å¦ĤåIJĮ
    -0.08
    æĿijåŃIJ
    -0.08
    ÑĻ
    -0.08
    -nil
    -0.08
    POSITIVE LOGITS
    kes
    0.10
     же
    0.09
    ched
    0.08
    ä¼´
    0.08
    elocity
    0.08
    å®īå±ħ
    0.08
    å¸ģ
    0.08
    ÑĦÑĤ
    0.08
    urement
    0.08
    anol
    0.08
    Activations Density 0.057%

    No Known Activations