© 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. 48533
    Prev
    Next
    INDEX
    Explanations

    immaculate, impeccably, Mac, car, laminar

    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
    ↵
    -0.08
    ä¸įç¡®å®ļ
    -0.08
    åŁºæľ¬æĥħåĨµ
    -0.08
    hip
    -0.08
    /cal
    -0.07
     Johannesburg
    -0.07
    积æŀģæĢ§
    -0.07
     Ars
    -0.07
    amble
    -0.07
     saint
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.12
    ä¸İåIJ¦
    0.11
    ÂŃi
    0.10
    主æĦı
    0.10
    è°·çĪ±
    0.10
    棣
    0.09
    íĺĢ
    0.09
    /il
    0.09
    íŀĪ
    0.09
    itude
    0.09
    Activations Density 0.007%

    No Known Activations