© 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. 53784
    Prev
    Next
    INDEX
    Explanations

    impressive achievements or qualities

    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
    sWith
    -0.11
    æĥħæĻ¯
    -0.10
    stro
    -0.10
    èĪ
    -0.09
    вел
    -0.09
    iens
    -0.09
    bies
    -0.09
    æĥħå¢ĥ
    -0.09
    à¸ªà¸łà¸²à¸ŀ
    -0.09
    ched
    -0.09
    POSITIVE LOGITS
    heid
    0.10
     обоÑĢ
    0.09
    ment
    0.09
    LY
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
     جدا
    0.08
    cket
    0.08
     enough
    0.08
     slam
    0.08
    ä¸Ńå¤ĸ
    0.08
    Activations Density 0.004%

    No Known Activations