© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21126
    Prev
    Next
    INDEX
    Explanations

    get in touch or contact

    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
    ä½ľä¸ºä¸ĢåIJį
    -0.09
    avid
    -0.09
     Beg
    -0.09
    erd
    -0.08
    _REGISTRY
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    üb
    -0.08
    åĬ¾
    -0.08
    thesis
    -0.08
     rg
    -0.08
    POSITIVE LOGITS
    èģĶç³»
    0.26
     contact
    0.21
    contact
    0.20
     Kontakt
    0.17
    .contact
    0.17
    Contact
    0.17
     Contact
    0.17
     contacto
    0.17
    èģĶç³»æĸ¹å¼ı
    0.17
    -contact
    0.17
    Activations Density 0.056%

    No Known Activations