© 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. 61389
    Prev
    Next
    INDEX
    Explanations

    man 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
    åĤ¬
    -0.09
    ä¼Ľ
    -0.08
    涨
    -0.08
    à¹Ĥà¸Ħ
    -0.08
    omens
    -0.08
    cpu
    -0.08
    表çİ°
    -0.08
    .codes
    -0.08
    ä¸ĵ项
    -0.08
    éĹ®éĹ®
    -0.08
    POSITIVE LOGITS
    æ³¼
    0.11
    çļĦçģµéŃĤ
    0.10
    åĬ¡å®ŀ
    0.10
    åĪĽä¸ļ
    0.10
    æķıæĦŁ
    0.10
    è°·
    0.10
    ä¸įå¼Ģ
    0.09
    çļĦæĹ¶ä»£
    0.09
    ä¹ĭæĥħ
    0.09
    åĵģæł¼
    0.09
    Activations Density 0.075%

    No Known Activations