© 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. 34993
    Prev
    Next
    INDEX
    Explanations

    legal and family 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
    æ¸ħç®Ĺ
    -0.09
     tá»ij
    -0.09
    pod
    -0.09
    çijķ
    -0.08
    оваÑĤÑĮ
    -0.08
    æģ¹
    -0.08
    [Byte
    -0.08
    æĬķè¯ī
    -0.08
    窨
    -0.08
     (::
    -0.08
    POSITIVE LOGITS
    åĪĩ
    0.10
    äºĭå®ľ
    0.09
    æĬļ
    0.09
    è¡Ķ
    0.08
    çľ·
    0.08
     ÑģÑĩиÑĤа
    0.08
    éĤ£ä½į
    0.08
    建ç«ĭäºĨ
    0.08
    æĤĸ
    0.08
     Www
    0.08
    Activations Density 0.018%

    No Known Activations