© 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. 8029
    Prev
    Next
    INDEX
    Explanations

    this time

    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
    ä½Ĩä¸įéĻIJ
    -0.08
    ç½ijæł¼
    -0.08
     Fal
    -0.08
    lew
    -0.08
    çĽ²
    -0.08
     wishlist
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    summ
    -0.08
    le
    -0.08
    lep
    -0.08
    POSITIVE LOGITS
    è§Ħ模æľĢ大
    0.10
    ANNER
    0.09
    è§Ħ模
    0.09
    ãģĬ話
    0.09
    -ci
    0.09
    gor
    0.09
    rire
    0.09
    abouts
    0.09
    ä¸Ĭ次
    0.09
    æĩĭ
    0.09
    Activations Density 0.010%

    No Known Activations