© 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. 55159
    Prev
    Next
    INDEX
    Explanations

    multiple configuration options

    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
    aty
    -0.08
    窦
    -0.08
    _corpus
    -0.08
    åĴķ
    -0.08
     tang
    -0.08
    _sd
    -0.08
    imap
    -0.08
    å²³
    -0.08
    chia
    -0.08
    à¸ģà¸Ķ
    -0.08
    POSITIVE LOGITS
    为客æĪ·
    0.12
    ä¸ļåĨħ
    0.10
    åĨĹ
    0.09
    æ¸ħæ¥ļ
    0.09
    åħ¸åŀĭçļĦ
    0.08
    éĢ»è¾ij
    0.08
    æĬ±
    0.08
    ç¼ĸç¨ĭ
    0.08
    åľ¨çİ°åľº
    0.08
    èłķ
    0.08
    Activations Density 0.288%

    No Known Activations