© 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. 54594
    Prev
    Next
    INDEX
    Explanations

    exposure to

    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
    à¹ģà¸Ĺ
    -0.09
    UNC
    -0.08
    unc
    -0.08
    awi
    -0.08
    stä
    -0.08
     surprise
    -0.08
    inking
    -0.08
    ä¸Ģ声
    -0.08
    Ŀ
    -0.08
    worth
    -0.08
    POSITIVE LOGITS
    ively
    0.10
    æĻ°
    0.10
    Ìģ
    0.10
    CLAIM
    0.09
    æ¶ķ
    0.09
    ansion
    0.09
    éľ²
    0.09
    sic
    0.09
    ible
    0.09
     wrench
    0.09
    Activations Density 0.043%

    No Known Activations