© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52814
    Prev
    Next
    INDEX
    Explanations

    nominated for awards

    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
    æĪIJæŀľ
    -0.10
    é²ľ
    -0.08
    ernals
    -0.08
    éĿĴ
    -0.08
     Dew
    -0.08
    ç¼Ŀ
    -0.08
     Hag
    -0.08
    _MACRO
    -0.08
    ç»
    -0.08
    опÑĢеделен
    -0.08
    POSITIVE LOGITS
    å¥ĸ项
    0.10
    åħį
    0.10
    ç¬¬åĽĽå±Ĭ
    0.10
    第ä¸ĥå±Ĭ
    0.10
    æĿ¯
    0.10
    æĪĪ
    0.09
    æĹĦ
    0.09
    第ä¸īå±Ĭ
    0.09
    crit
    0.09
    çģµæ°Ķ
    0.09
    Activations Density 0.097%

    No Known Activations