© 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. 55878
    Prev
    Next
    INDEX
    Explanations

    ranking and placement

    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
    åĢ¾
    -0.09
    å®ĥ们
    -0.09
    rompt
    -0.08
    åĭ¤åĬ³
    -0.08
    级åĪ«çļĦ
    -0.08
     Rudd
    -0.08
    iban
    -0.08
    ç¡®
    -0.08
    ATUS
    -0.08
    íģ°
    -0.08
    POSITIVE LOGITS
    æ²®
    0.09
    зд
    0.09
    鸱
    0.08
    书åºĹ
    0.08
    åĽ½ç±į
    0.08
    æľīåĬ©
    0.08
    åħļçļĦ建设
    0.08
    rid
    0.08
     Pa
    0.08
    ritte
    0.08
    Activations Density 0.017%

    No Known Activations