© 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. 21376
    Prev
    Next
    INDEX
    Explanations

    or so

    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
     воÑģ
    -0.10
    æĺ¯ä»Ģä¹Īåij¢
    -0.10
    ipl
    -0.09
    çļĦåīįæıIJä¸ĭ
    -0.08
    uits
    -0.08
    CI
    -0.08
    åĿļåĽº
    -0.08
    elems
    -0.08
     herr
    -0.08
    mur
    -0.08
    POSITIVE LOGITS
     dozen
    0.10
    bian
    0.09
    rf
    0.09
    ëĿ½
    0.09
    adox
    0.08
    ãģ»ãģ©
    0.08
    å·®ä¸įå¤ļ
    0.08
    æĸ°åªĴä½ĵ
    0.08
    è§IJ
    0.08
    æµ®åĬ¨
    0.08
    Activations Density 0.024%

    No Known Activations