© 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. 48127
    Prev
    Next
    INDEX
    Explanations

    privatization of

    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
    éĢģå¾Ģ
    -0.10
    èĩªçIJĨ
    -0.09
    åŁ
    -0.09
    atters
    -0.09
    åĦ¿å¥³
    -0.09
    éķĹ
    -0.09
    åŃIJéĩĮ
    -0.09
    è§Ħ模以ä¸Ĭ
    -0.09
    è±ī
    -0.09
    龸
    -0.09
    POSITIVE LOGITS
    ization
    0.08
    ikan
    0.08
    iche
    0.08
    æ·ĭ
    0.08
     Masc
    0.08
    èĭ¥å¹²
    0.08
    å§ĵ
    0.08
    èıŁ
    0.08
    å¼ĢæĿ¥
    0.08
    åĽŀ头çľĭ
    0.08
    Activations Density 0.010%

    No Known Activations