© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20462
    Prev
    Next
    INDEX
    Explanations

    "ac" prefix + various endings

    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
    ared
    -0.09
    åı£å¾Ħ
    -0.09
    eds
    -0.09
    AWN
    -0.09
    EDIA
    -0.09
    wart
    -0.09
    دار
    -0.09
    没åħ³ç³»
    -0.08
    祯
    -0.08
    ischen
    -0.08
    POSITIVE LOGITS
    çī¡
    0.10
    0.10
    åĿŀ
    0.09
    åľ¨çº¿åĴ¨è¯¢
    0.09
    æ¯ı人
    0.09
    éĻĤ
    0.08
     Boh
    0.08
    æļĦ
    0.08
    ç¨įç¨į
    0.08
    岬
    0.08
    Activations Density 0.001%

    No Known Activations