© 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. 61106
    Prev
    Next
    INDEX
    Explanations

    ( followed by number

    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
    çķļ
    -0.10
    TED
    -0.09
    nosis
    -0.09
    éĥĬ
    -0.08
    建ç«ĭèµ·
    -0.08
     sore
    -0.08
    å³Ń
    -0.08
    ç¼Ĺ
    -0.08
    _buffers
    -0.08
    å°¼æĸ¯
    -0.08
    POSITIVE LOGITS
    ç³»åĪĹ
    0.10
    ä¾®
    0.10
    ãĤ·ãĥªãĥ¼ãĤº
    0.09
    uez
    0.09
    ä»ĬçĶŁ
    0.09
    çĶľèľľ
    0.09
    寤
    0.09
    åIJ«ä¹ī
    0.08
    å¯IJ
    0.08
    æŀľå®ŀ
    0.08
    Activations Density 0.259%

    No Known Activations