© 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. 3965
    Prev
    Next
    INDEX
    Explanations

    one of

    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
     Majority
    -0.09
    ><![
    -0.09
    ÑĩаÑĤ
    -0.09
    çĶ»åĥı
    -0.08
     Lump
    -0.08
     majority
    -0.08
     Monaco
    -0.08
    æĢħ
    -0.08
    mentioned
    -0.08
    被æ·ĺæ±°
    -0.08
    POSITIVE LOGITS
    æİĸ
    0.09
    /LICENSE
    0.09
    éħ±æ²¹
    0.09
    åħ±åĴĮåĽ½
    0.09
    åħ¸åŀĭçļĦ
    0.09
    ást
    0.08
    姬
    0.08
    æĹĭå¾ĭ
    0.08
    解èĦ±
    0.08
    TemplateName
    0.08
    Activations Density 0.044%

    No Known Activations