© 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. 5484
    Prev
    Next
    INDEX
    Explanations

    Subject:

    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
    å¹´åºķåīį
    -0.09
    ä¸įä¸Ĭ
    -0.08
    å¨ĺå¨ĺ
    -0.08
    ext
    -0.08
     Crest
    -0.08
    ä¸įåIJ«
    -0.08
     å¯
    -0.08
    inded
    -0.08
    assi
    -0.08
    ritis
    -0.08
    POSITIVE LOGITS
    éºĵ
    0.09
    æĪIJéķ¿
    0.09
    elta
    0.09
    ç»ıåİĨ
    0.08
    eltas
    0.08
    oad
    0.08
    esimal
    0.08
    ä¸Ńåħ³
    0.08
    ä¸ĥæĺŁ
    0.08
    åıijå±ķ模å¼ı
    0.08
    Activations Density 0.013%

    No Known Activations