© 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. 7166
    Prev
    Next
    INDEX
    Explanations

    product description, dating sites, early prototype, project plan, senior professional, practice guidelines

    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
    æĿ¾å¼Ľ
    -0.08
    ota
    -0.08
    7
    -0.08
    2
    -0.08
     Extras
    -0.08
    1
    -0.08
    0
    -0.07
    9
    -0.07
     unsur
    -0.07
    ç¡®
    -0.07
    POSITIVE LOGITS
    åį³å°Ĩ
    0.11
    åį³å°ĨåĪ°æĿ¥
    0.11
    é³
    0.11
    æŁIJç§į
    0.10
    åĪĽä¸ļ
    0.10
    psc
    0.10
    åĪĿåĪĽ
    0.10
    onyms
    0.10
    梦è§ģ
    0.10
    éĿ¢ä¸´çļĦ
    0.09
    Activations Density 0.171%

    No Known Activations