© 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. 35575
    Prev
    Next
    INDEX
    Explanations

    mechanical components

    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
    çłº
    -0.09
    æķ´é¡¿
    -0.09
     Yas
    -0.08
    çģ«çĤ¬
    -0.08
    空éĹ´
    -0.08
    çĢ¹
    -0.08
    URN
    -0.08
    æ¼Ĥ
    -0.08
     Myst
    -0.08
    严
    -0.08
    POSITIVE LOGITS
     меÑħанизм
    0.10
    åĴĮå°ļ
    0.10
    ä¼łéĢĴ
    0.10
    éª
    0.10
     Mai
    0.09
    çīĻ
    0.09
    å°ıèħ¿
    0.09
     Adobe
    0.09
    å±±åĿ¡
    0.09
    Adobe
    0.09
    Activations Density 0.157%

    No Known Activations