© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10039
    Prev
    Next
    INDEX
    Explanations

    at the hands of

    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
    èĥ½å¾ĹåĪ°
    -0.10
    åīĸ
    -0.09
    羣åĪĩ
    -0.09
    :normal
    -0.08
    æĦŁåħ´è¶£
    -0.08
     Clair
    -0.08
    åľ¨åŃ¦æł¡
    -0.08
    åģ¥åº·çļĦ
    -0.08
    ä»İæł¹æľ¬ä¸Ĭ
    -0.08
     Paladin
    -0.08
    POSITIVE LOGITS
    olute
    0.09
    çŁ¥
    0.09
    æĵį
    0.08
    .erb
    0.08
    roma
    0.08
    ERA
    0.08
    å¸ĥ
    0.08
    æĪij以为
    0.08
    yre
    0.08
    ç³»
    0.08
    Activations Density 0.002%

    No Known Activations