© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37484
    Prev
    Next
    INDEX
    Explanations

    seem to verb

    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
    åĴĮæĶ¯æĮģ
    -0.11
    ä¸į失
    -0.10
    çľĭä¼¼
    -0.09
     seemingly
    -0.09
    ç§ijåѦåıijå±ķ
    -0.09
    ä½łè§īå¾Ĺ
    -0.09
    æħİéĩį
    -0.09
    à¸IJาà¸Ļ
    -0.09
    æĽ´å¥½çļĦ
    -0.08
    åı·ç§°
    -0.08
    POSITIVE LOGITS
    èł
    0.10
    rame
    0.10
    eam
    0.09
    ulary
    0.08
    ching
    0.08
    ars
    0.08
    scape
    0.08
    è¦ģçĶ¨
    0.08
     jac
    0.08
    -eyed
    0.08
    Activations Density 0.032%

    No Known Activations