© 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. 22266
    Prev
    Next
    INDEX
    Explanations

    xml version or language-based content

    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°¸æģĴ
    -0.09
     licensors
    -0.08
     Shut
    -0.08
    æĪĺ
    -0.08
     ì·¨
    -0.08
    轸
    -0.08
    asion
    -0.08
    Licensed
    -0.08
    .debugLine
    -0.08
    èĤ©
    -0.08
    POSITIVE LOGITS
    åģļå·¥
    0.12
    åīįä¸Ģ天
    0.11
    å½ĵ天
    0.11
    å½ĵæĻļ
    0.10
    è®©ä½ł
    0.10
    æ»ĭåij³
    0.09
    æľįåĬ¡åijĺ
    0.09
    åĴ¬
    0.09
    abi
    0.09
    cep
    0.09
    Activations Density 0.027%

    No Known Activations