© 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. 58830
    Prev
    Next
    INDEX
    Explanations

    $ amount preceding units

    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
    é«ĺ端
    -0.09
    ajas
    -0.09
    ATIC
    -0.08
    shr
    -0.08
     Rune
    -0.08
    ราย
    -0.08
    CDATA
    -0.08
    éħ±
    -0.08
    burst
    -0.08
    ifen
    -0.07
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.11
    æ¿ĢçĥĪçļĦ
    0.11
    éĥ½ä¸įæĺ¯
    0.09
    æľĢåŁºæľ¬çļĦ
    0.09
    忽
    0.09
    çĭIJ
    0.09
     pois
    0.09
    人æ°ijåĮ»éĻ¢
    0.09
    æĻ®éĢļçļĦ
    0.09
    licit
    0.09
    Activations Density 0.046%

    No Known Activations