© 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. 36525
    Prev
    Next
    INDEX
    Explanations

    bringing with

    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
    æĹłåħ³
    -0.09
    avis
    -0.09
     Cush
    -0.09
    éĿ´
    -0.09
    åĬ³
    -0.08
     //=
    -0.08
    èĪĴéĢĤ
    -0.08
    лаÑĤ
    -0.08
    pth
    -0.08
    æĹłæķ°æ¬¡
    -0.08
    POSITIVE LOGITS
    éļıä¹ĭ
    0.14
    ä¹Łéļıä¹ĭ
    0.13
    å®ĥçļĦ
    0.10
    é¡»
    0.10
     dabei
    0.10
    èĩªæĿ¥
    0.09
     ÑģооÑĤвеÑĤ
    0.09
    çļĦä¸ĢéĿ¢
    0.09
     therein
    0.09
    çĿĢæīĭ
    0.09
    Activations Density 0.041%

    No Known Activations