© 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. 27776
    Prev
    Next
    INDEX
    Explanations

    subscribe to

    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
    sten
    -0.09
    å¾Ĺå¾Ī
    -0.09
    ENSE
    -0.09
     má»Ŀi
    -0.09
    åĿª
    -0.08
     Soda
    -0.08
     ens
    -0.08
    计ç®ĹåĻ¨
    -0.08
    åĩĨ
    -0.08
    èĩ³æĸ¼
    -0.08
    POSITIVE LOGITS
    ä¸Ńåįİ
    0.09
    uzzi
    0.09
    chein
    0.08
    atest
    0.08
    ä½łçļĦ
    0.08
    eft
    0.08
    æŀ¢
    0.08
     disproportion
    0.08
    .getLength
    0.08
    lep
    0.08
    Activations Density 0.007%

    No Known Activations