© 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. 7344
    Prev
    Next
    INDEX
    Explanations

    from a range 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
    æħ§
    -0.10
    æĹłå£°
    -0.09
    çİ·
    -0.09
    åĴļ
    -0.08
    çļĵ
    -0.08
    çħ¦
    -0.08
    èĪĮ头
    -0.08
    æĵħèĩª
    -0.08
    çªľ
    -0.08
    ynth
    -0.08
    POSITIVE LOGITS
    asca
    0.11
     пÑĢоÑĨед
    0.09
    ä»Ŀ
    0.09
     Levy
    0.09
    ä¸Ģå¼Ģå§ĭ
    0.09
    неÑĨ
    0.09
    ifle
    0.09
    ä¼ĹæīĢ
    0.09
    大大å°ı
    0.09
    ngth
    0.08
    Activations Density 0.083%

    No Known Activations