© 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. 30799
    Prev
    Next
    INDEX
    Explanations

    difference between X and Y

    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
    éĻĨ
    -0.11
    éĻ¸
    -0.09
    atures
    -0.09
    imbus
    -0.09
    åı¯è§Ĥ
    -0.08
     counterpart
    -0.08
    ogra
    -0.08
    anium
    -0.08
    PAL
    -0.08
    æķı
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.11
    羣æŃ£
    0.10
    ä»ħä»ħæĺ¯
    0.10
    ç´§æĢ¥
    0.10
    ä»įå°Ĩ
    0.09
    羣æŃ£çļĦ
    0.09
    ä»ħä»ħ
    0.09
    éĤ£æ®µ
    0.08
    _editor
    0.08
    tek
    0.08
    Activations Density 0.062%

    No Known Activations