© 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. 56081
    Prev
    Next
    INDEX
    Explanations

    latest news and info

    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
     некоÑĤоÑĢÑĭе
    -0.10
    æıIJä¾ĽæĽ´å¤ļ
    -0.09
    æĺ¯è¦ģ
    -0.09
    çļĦä¸ĢäºĽ
    -0.09
    两款
    -0.09
     ALWAYS
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.08
    é£Łçī©
    -0.08
    è¿Ļ段
    -0.08
    éĤ£æ®µ
    -0.08
    POSITIVE LOGITS
    é£İåIJ¹
    0.08
    åĺī
    0.08
    icom
    0.08
    ToOne
    0.08
    маÑĢ
    0.08
    çIJĨ
    0.08
    _outline
    0.08
    ¢åįķ
    0.08
    ë§IJ
    0.08
    licated
    0.08
    Activations Density 0.082%

    No Known Activations