© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    batting practice stats and average

    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
    antic
    -0.09
    好äºĭ
    -0.08
    ÑĩаÑĤ
    -0.08
    riot
    -0.08
    obody
    -0.08
    éħį件
    -0.08
     Ord
    -0.08
     ord
    -0.08
    DR
    -0.08
    ardy
    -0.08
    POSITIVE LOGITS
    positor
    0.10
    amu
    0.09
    istic
    0.09
    æŁ
    0.09
    çī¹çĤ¹æĺ¯
    0.09
    è¯ĭ
    0.09
    uet
    0.09
    æĺĥ
    0.09
     Twice
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    Activations Density 0.005%

    No Known Activations