© 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. 16963
    Prev
    Next
    INDEX
    Explanations

    patients and healthcare offerings

    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
    odie
    -0.11
    æĺ§
    -0.10
    é²ľæĺİ
    -0.10
    å¥ĭ
    -0.09
    åħĢ
    -0.09
    _PRINTF
    -0.09
    æĹº
    -0.09
    éĢŀ
    -0.09
    æĻļæĬ¥
    -0.09
    èµĺ
    -0.09
    POSITIVE LOGITS
    家çĶ¨
    0.09
    Locator
    0.09
     Unidos
    0.09
    ÑĢоз
    0.09
    峪
    0.09
     Gat
    0.09
    ç»ĻæĪij
    0.08
    å®īæİĴ
    0.08
     RX
    0.08
    导
    0.08
    Activations Density 0.151%

    No Known Activations