© 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. 50488
    Prev
    Next
    INDEX
    Explanations

    trial court

    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
    åĤ»
    -0.10
    第ä¸īæĸ¹
    -0.09
    éķ°
    -0.09
    éļıå¤Ħ
    -0.08
    ç»Ī
    -0.08
     Ran
    -0.08
    éķij
    -0.08
    ì§Ŀ
    -0.08
    ament
    -0.08
    jiang
    -0.08
    POSITIVE LOGITS
    æĪ¡
    0.10
     Kash
    0.09
    /plain
    0.09
    ãĥ¯ãĥ³
    0.09
    _DU
    0.08
    ä¸įåIJĮæĦı
    0.08
    å¾ģ
    0.08
     Ill
    0.08
    óa
    0.08
    é£İè²Į
    0.08
    Activations Density 0.025%

    No Known Activations