© 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. 12044
    Prev
    Next
    INDEX
    Explanations

    else or other

    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
    lify
    -0.09
    ionario
    -0.09
    éķ¿å¤§
    -0.09
    Ê°
    -0.09
    æľŁåĨħ
    -0.08
     Ñģобой
    -0.08
    éĺħåİĨ
    -0.08
    ieri
    -0.08
     جدا
    -0.08
    (rb
    -0.08
    POSITIVE LOGITS
    åī©
    0.11
    èĤĩ
    0.10
    ç§įç§į
    0.10
    ä¹Łå¸ĮæľĽ
    0.09
    æĩĭ
    0.09
    ds
    0.09
    æŀī
    0.09
    åī©ä¸ĭçļĦ
    0.09
    åĴİ
    0.09
    åIJĦé¡¹å·¥ä½ľ
    0.09
    Activations Density 0.009%

    No Known Activations