© 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. 38600
    Prev
    Next
    INDEX
    Explanations

    cricket betting odds comparison

    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
    олж
    -0.09
    reau
    -0.09
    å¥ij
    -0.09
    ç§ī
    -0.08
    _hd
    -0.08
    Grace
    -0.08
    ottage
    -0.08
    æıĨ
    -0.08
    _PIPELINE
    -0.08
     grace
    -0.08
    POSITIVE LOGITS
    æĬ¼
    0.11
    é«ĺåĩº
    0.09
    åıĮæĸ¹
    0.09
    åģıå·®
    0.09
    åĢĴå¡Į
    0.09
    èµ°åĬ¿
    0.08
    ︱
    0.08
    æī¶
    0.08
    åºĦ
    0.08
    æłĩçļĦ
    0.08
    Activations Density 0.029%

    No Known Activations