© 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. 27494
    Prev
    Next
    INDEX
    Explanations

    by followed by a differentiator

    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
    èĹķ
    -0.09
     Exc
    -0.08
    -duty
    -0.08
    uest
    -0.08
    Exc
    -0.08
    第ä¸ī代
    -0.08
     اÙĦأساس
    -0.08
    бо
    -0.08
    åĽ°
    -0.08
    [++
    -0.08
    POSITIVE LOGITS
    çľģ份
    0.14
    åľ°åŁŁ
    0.14
    åľ°åĮºçļĦ
    0.11
    ç±»åĪ«
    0.10
    åľ°åĮº
    0.10
    ç§įæĹı
    0.10
    è°Ĺ
    0.10
    æŶéĹ´æ®µ
    0.10
     capita
    0.09
    åľºåIJĪ
    0.09
    Activations Density 0.105%

    No Known Activations