© 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. 48263
    Prev
    Next
    INDEX
    Explanations

    names ending in 'n' or 'man'

    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
    åıijè¾¾åĽ½å®¶
    -0.13
    ä¸ĸçķĮåIJĦåĽ½
    -0.10
    ä¸ĸçķĮåIJĦåľ°
    -0.10
    éĻĮçĶŁäºº
    -0.09
    ä¼ij
    -0.09
    ä¸Ń举
    -0.09
    erson
    -0.09
    åIJĦåĽ½
    -0.09
    åįİ举
    -0.09
    hammer
    -0.08
    POSITIVE LOGITS
    è¿Ķ乡
    0.09
    为代表çļĦ
    0.09
     timeval
    0.09
    売ãĤĮ
    0.09
    viously
    0.08
    é¢ĨåĨĽ
    0.08
     ÙĪز
    0.08
    è¯Ŀ
    0.08
    omo
    0.08
    urrection
    0.08
    Activations Density 0.181%

    No Known Activations