© 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. 30304
    Prev
    Next
    INDEX
    Explanations

    estate and probate matters

    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
    ä¼łæİĪ
    -0.09
     Ludwig
    -0.09
    çħĮ
    -0.09
    çĶ³è´Ń
    -0.08
    æ²ī
    -0.08
     Dank
    -0.08
     wur
    -0.08
     Inserts
    -0.08
    hte
    -0.08
    enus
    -0.08
    POSITIVE LOGITS
    æ¸ħæĺİ
    0.10
    æ¸ħçIJĨ
    0.10
    æ¸ħç®Ĺ
    0.09
    é¹Ĭ
    0.09
    æŃ»èĢħ
    0.09
    æľīåħ´è¶£
    0.08
    ÃŃm
    0.08
    æĸĻçIJĨ
    0.08
    è°¨æħİ
    0.08
    zej
    0.08
    Activations Density 0.137%

    No Known Activations