© 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. 35820
    Prev
    Next
    INDEX
    Explanations

    In particular

    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
    ลà¸ĩ
    -0.10
    俨
    -0.10
    scheme
    -0.09
    æīįç®Ĺ
    -0.09
    æĿĥå¨ģ
    -0.09
    .px
    -0.09
    çķĭ
    -0.09
     rÃłng
    -0.09
    好åIJ§
    -0.09
    å¸Ľ
    -0.09
    POSITIVE LOGITS
    èĹı
    0.10
    å¿ĥæĢĿ
    0.09
    urr
    0.08
    éĵŃè®°
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    çļĦæĹ¥åŃIJéĩĮ
    0.08
    æ¯ħåĬĽ
    0.08
    lâ
    0.08
    itial
    0.08
    æĶ¶æĶ¯
    0.08
    Activations Density 0.031%

    No Known Activations