© 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. 56980
    Prev
    Next
    INDEX
    Explanations

    deploying application servers

    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
    DAY
    -0.10
    éĢļè¡Į
    -0.10
    åĩºç¤º
    -0.09
     rab
    -0.09
    .lon
    -0.09
    ä¸IJ
    -0.09
    诬
    -0.09
    çĦķ
    -0.09
    éĴī
    -0.09
    ModelState
    -0.09
    POSITIVE LOGITS
    cob
    0.08
    SSL
    0.08
    ç¼Ń
    0.08
    ðŁĵĮ
    0.08
    é¼ĵ
    0.08
    ãĥľãĥ¼
    0.08
    绾
    0.08
    ä¸įå®ļ
    0.08
    åIJijãģį
    0.08
    èĭŀ
    0.08
    Activations Density 0.229%

    No Known Activations