© 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. 31292
    Prev
    Next
    INDEX
    Explanations

    Rice

    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
    à¤Ŀ
    -0.10
     Forbes
    -0.09
     ê·¸ëłĩ
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    ICODE
    -0.09
    ors
    -0.08
    cern
    -0.08
     ÙĨÙĤ
    -0.08
    arde
    -0.08
    æ¹¾åĮº
    -0.08
    POSITIVE LOGITS
    _BB
    0.09
    0.09
    opper
    0.09
    -quarters
    0.09
     Evel
    0.09
    ämp
    0.08
     ÐĴлад
    0.08
    fully
    0.08
    æĽ´éĩįè¦ģçļĦ
    0.08
     пен
    0.08
    Activations Density 0.003%

    No Known Activations