© 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. 23270
    Prev
    Next
    INDEX
    Explanations

    splicing, variants, exons, introns, transcription

    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
    饥
    -0.12
    æĨ§
    -0.11
    eldon
    -0.10
    伸åĩº
    -0.10
    åķ§
    -0.09
    eldo
    -0.09
    车载
    -0.09
    ä½İ声
    -0.09
    ä½IJ
    -0.09
    _approx
    -0.09
    POSITIVE LOGITS
    åIJĪæ³ķ
    0.09
    人大
    0.09
    -stock
    0.09
    ehr
    0.08
    alls
    0.08
    å·¥æľŁ
    0.08
    usp
    0.08
    è¹Ī
    0.08
    å¿ĥæĻº
    0.08
    ç½¢äºĨ
    0.08
    Activations Density 0.249%

    No Known Activations