© 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. 36283
    Prev
    Next
    INDEX
    Explanations

    microRNA

    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
    éĹ»
    -0.10
     Goldman
    -0.09
     ÑĥÑģл
    -0.09
    inyin
    -0.09
    éķı
    -0.09
    游åĩ»
    -0.09
    éĽªå±±
    -0.09
    æīī
    -0.09
    å¿IJ
    -0.09
    åı®
    -0.09
    POSITIVE LOGITS
    æľªå©ļ
    0.08
    å¿ĥæĥ³
    0.08
    RegularExpression
    0.08
    ä¿Ń
    0.08
    anut
    0.08
    çīµå¼ķ
    0.08
    æĤ¬
    0.08
    åĩ¶æīĭ
    0.08
     Clone
    0.08
     delivery
    0.08
    Activations Density 0.130%

    No Known Activations