© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19717
    Prev
    Next
    INDEX
    Explanations

    you statements

    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
    unta
    -0.09
    帮åĬ©
    -0.08
    ÑĢÑĥг
    -0.08
    omic
    -0.08
    rame
    -0.08
    -going
    -0.08
    rong
    -0.08
    boarding
    -0.08
     Guatemala
    -0.08
    æĮīæŶ
    -0.08
    POSITIVE LOGITS
    èįĴ
    0.10
    æĹĹä¸ĭ
    0.09
    æĻºåºĵ
    0.09
    çģ«åĬĽ
    0.08
    æ®ĭ
    0.08
    ICS
    0.08
    éĥ½åĸľæ¬¢
    0.08
    åħī彩
    0.08
    åľ¨æ¸¸æĪıä¸Ń
    0.08
    éĢıæĺİ
    0.08
    Activations Density 0.123%

    No Known Activations