© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    local communities and residents

    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
    éĴī
    -0.12
    æŶæŶ
    -0.10
    èĩªçĦ¶èĢĮ
    -0.10
    诸èijĽ
    -0.09
    æľ¬ç½ijç«Ļ
    -0.08
    _nl
    -0.08
    (Of
    -0.07
    (exports
    -0.07
     Celtic
    -0.07
    æŁ¥çľĭ详æĥħ
    -0.07
    POSITIVE LOGITS
    oug
    0.10
    ä¸įåĨįæĺ¯
    0.09
    æ©Ļ
    0.09
    迺
    0.09
    è¡Įä¸ļä¸Ń
    0.09
    æĭĽåĭŁ
    0.08
    æIJľæķij
    0.08
    Ñıд
    0.08
    åıĬ以ä¸Ĭ
    0.08
    ohana
    0.08
    Activations Density 0.016%

    No Known Activations