© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20467
    Prev
    Next
    INDEX
    Explanations

    Cape Verdean

    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
    èļĮ
    -0.10
    æľ«
    -0.10
    OptionsMenu
    -0.10
    elage
    -0.10
    isher
    -0.09
    å½±éĻ¢
    -0.09
    åĽłåľ°åĪ¶å®ľ
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    è¾Ĩ车
    -0.09
    æ±Łæ·®
    -0.09
    POSITIVE LOGITS
    åĬĿ
    0.10
     gob
    0.08
    lest
    0.08
    æį§
    0.08
    opening
    0.08
    ê°ij
    0.08
     Whitney
    0.07
     drafts
    0.07
    çĺģ
    0.07
     geg
    0.07
    Activations Density 0.007%

    No Known Activations