© 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. 37951
    Prev
    Next
    INDEX
    Explanations

    fewer resources, more value

    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
    ç´¯
    -0.12
    Ùħرة
    -0.10
    ouv
    -0.09
    éĢIJ
    -0.09
    è´¯
    -0.09
    åį§
    -0.09
    åı¯ä»¥çĽ´æİ¥
    -0.09
    ç´¯äºĨ
    -0.09
    åĽº
    -0.09
    Dod
    -0.09
    POSITIVE LOGITS
    æľīéĻIJ
    0.12
    å°ijãģªãģĦ
    0.09
    culos
    0.09
    æķĪ
    0.09
     fewer
    0.09
     бÑİджеÑĤ
    0.08
     thinner
    0.08
    éĻIJ度
    0.08
    á»Ļi
    0.08
     budgets
    0.08
    Activations Density 0.103%

    No Known Activations