© 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. 36296
    Prev
    Next
    INDEX
    Explanations

    radioactive isotopes and uptake

    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
    ением
    -0.10
    çķĻå®Ī
    -0.09
    .uuid
    -0.09
    æĮ¨
    -0.09
    ollo
    -0.09
    ä¹Łä¸įéĶĻ
    -0.08
    знаком
    -0.08
    åĽ½éĻħåĮĸ
    -0.08
    _SZ
    -0.08
    åĢĴåľ¨
    -0.08
    POSITIVE LOGITS
    好äºĭ
    0.09
    èĩĤ
    0.09
    辨
    0.09
    åĩłä½ķ
    0.08
    å¤ĸè§Ĥ
    0.08
    rial
    0.08
     Kis
    0.08
    ibal
    0.08
    åIJĪ
    0.08
    æĬĸ
    0.08
    Activations Density 0.275%

    No Known Activations