© 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. 11423
    Prev
    Next
    INDEX
    Explanations

    irregular, irrelevant, irritable

    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
    å¨ħ
    -0.09
    аÑĢÑĤ
    -0.09
    soever
    -0.09
    íĴĢ
    -0.09
    åĩĢåĢ¼
    -0.09
     Guil
    -0.09
    Ñĩи
    -0.08
    ä¸įåIJĮç¨ĭ度
    -0.08
    èµį
    -0.08
    èĪįå¾Ĺ
    -0.08
    POSITIVE LOGITS
    mond
    0.11
    enal
    0.09
    elong
    0.09
    ongs
    0.09
    abelle
    0.09
    quo
    0.09
    amples
    0.09
    å±ŀ
    0.09
    fully
    0.09
    ty
    0.09
    Activations Density 0.037%

    No Known Activations