© 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. 55282
    Prev
    Next
    INDEX
    Explanations

    make your

    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
     Marsh
    -0.09
    çķĪ
    -0.09
    inki
    -0.09
    ä¸Ģéģį
    -0.09
    åĸij
    -0.08
     escal
    -0.08
    纪å§Ķ书记
    -0.08
    Marsh
    -0.08
     Wort
    -0.08
     ë¬
    -0.08
    POSITIVE LOGITS
    äºĭæĥħ
    0.11
    _filenames
    0.09
    æ¯ı次
    0.09
    çĶŁæ´»
    0.09
    ä»ĬåIJİ
    0.08
    æľ¬é¢Ĩ
    0.08
    ä¹ı
    0.08
    nable
    0.08
    夹
    0.08
    å²Ĥ
    0.08
    Activations Density 0.049%

    No Known Activations