© 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. 38602
    Prev
    Next
    INDEX
    Explanations

    not that [adjective/adverb]

    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
    coni
    -0.10
    éļıæŶ
    -0.09
    /TR
    -0.09
    è¶ħé¢Ŀ
    -0.08
    表æī¬
    -0.08
    社ä¼ļåĮĸ
    -0.08
    imity
    -0.08
    èįĶæŀĿ
    -0.08
    utive
    -0.08
    à¹Ģà¸ģ
    -0.08
    POSITIVE LOGITS
    çIJ¨
    0.10
    æĦıä¹īä¸Ĭ
    0.10
    éĶħ
    0.10
    oper
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.09
    éĢĬ
    0.09
    è®®äºĭ
    0.09
    éĴµ
    0.09
     Drinks
    0.09
    èµĦ产éĩįç»Ħ
    0.09
    Activations Density 0.015%

    No Known Activations