© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    money assets loss

    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
    eldorf
    -0.11
    èĭ«
    -0.10
    GIN
    -0.10
     closed
    -0.09
     Disclosure
    -0.09
    .Closed
    -0.09
    åĢ«
    -0.09
     Dank
    -0.09
    è®®
    -0.09
    èĢĥåı¤
    -0.09
    POSITIVE LOGITS
    财产
    0.12
    æľ¬éĩij
    0.11
    éĴ±
    0.11
    æįŁå¤±
    0.11
    åĽŀæĶ¶
    0.11
     loss
    0.11
     Loss
    0.10
    Loss
    0.10
    è´¢çī©
    0.10
    è´¢å¯Į
    0.10
    Activations Density 0.177%

    No Known Activations