© 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. 34537
    Prev
    Next
    INDEX
    Explanations

    mountains, summits, or geographical features

    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
    æ¨¡æł·
    -0.10
    é¥ŃåºĹ
    -0.10
    olk
    -0.09
    æģĴ
    -0.09
    çļĦåķĨåĵģ
    -0.09
    æĬ¼
    -0.09
    LAG
    -0.09
    åĻ©
    -0.09
    æĭľå¸ĪåѦèīº
    -0.09
    steen
    -0.09
    POSITIVE LOGITS
    uteur
    0.10
    æļĹ
    0.09
    认è¯Ĩ
    0.09
    entar
    0.08
    å®ŀéªĮ室
    0.08
    .son
    0.08
    éĤ£è¾¹
    0.08
    é»ı
    0.08
    оÑĤоÑĢ
    0.08
    lix
    0.08
    Activations Density 0.010%

    No Known Activations