© 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. 55081
    Prev
    Next
    INDEX
    Explanations

    escaping special characters

    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
    åĪİ
    -0.10
    æ²Ļåıij
    -0.09
    çĥı
    -0.09
    çģ£
    -0.09
    æįŀ
    -0.08
    建çŃij设计
    -0.08
    ä¸įåħ¬å¹³
    -0.08
    éĹ®è´£
    -0.08
    åı¹æģ¯
    -0.08
    殿
    -0.08
    POSITIVE LOGITS
    reserved
    0.09
    Reserved
    0.08
    èµ·åĪ°
    0.08
    è¶Ĭæĺ¯
    0.08
    éĿ¢çĽ®
    0.08
     Åŀe
    0.08
     Kı
    0.08
    slashes
    0.08
     Dav
    0.08
    ató
    0.08
    Activations Density 0.694%

    No Known Activations