© 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. 27142
    Prev
    Next
    INDEX
    Explanations

    description provided by or from

    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
    çľ©
    -0.09
    ään
    -0.09
    æ®Ĩ
    -0.09
    é¦ĸå¯Į
    -0.08
    åĶĩ
    -0.08
    æľĢåħĪ
    -0.08
    çĸĶ
    -0.08
    ware
    -0.08
    çĭIJ
    -0.08
    sponsor
    -0.08
    POSITIVE LOGITS
     Eff
    0.09
    æ°ĹãģĮ
    0.09
    æĻ¯åĮº
    0.09
    大éħĴåºĹ
    0.09
    æıIJä¾ĽçļĦ
    0.09
    isma
    0.09
    ä¸įåĨį
    0.08
    ozy
    0.08
    benh
    0.08
    大åİħ
    0.08
    Activations Density 0.004%

    No Known Activations