© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    .com URLs

    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
    idan
    -0.09
    驾é©Ń
    -0.09
    anyl
    -0.09
    æĴĤ
    -0.08
    æ·¡å®ļ
    -0.08
    æīĢæīĢ
    -0.08
    feld
    -0.08
    ç½¢
    -0.08
    èĮ¼
    -0.08
    ายà¸Ļ
    -0.08
    POSITIVE LOGITS
    иÑĪ
    0.09
    hte
    0.08
     portal
    0.08
    åįıåIJĮåıijå±ķ
    0.08
    .tw
    0.08
     üzerine
    0.08
    æĿ¡è§Ħå®ļ
    0.08
     phá»iji
    0.08
    å¸ĥ
    0.08
    æĦŁæĥħ
    0.08
    Activations Density 0.162%

    No Known Activations