© 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. 11645
    Prev
    Next
    INDEX
    Explanations

    market capitalization and valuation

    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
    æ¸ł
    -0.10
    å¤
    -0.10
    andler
    -0.09
    pike
    -0.09
    etics
    -0.09
     Indies
    -0.09
    å¼ĤæĢ§
    -0.09
    ods
    -0.08
    idian
    -0.08
    è¯ī
    -0.08
    POSITIVE LOGITS
    å¸ĤåĢ¼
    0.10
     Unlock
    0.08
     respons
    0.08
    é»į
    0.08
    åįķåįķ
    0.08
    æ½
    0.08
    æ·¡åĮĸ
    0.08
     circulation
    0.08
    åĿ¼
    0.08
    iale
    0.08
    Activations Density 0.020%

    No Known Activations