© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37483
    Prev
    Next
    INDEX
    Explanations

    Reasons, Things, Signs, Practices, Fun, Simple followed by verbs/pronouns

    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
    owie
    -0.10
    ä¸ĢåľĪ
    -0.09
    èĢIJ磨
    -0.09
    ä¸īå®¶
    -0.09
    ç¨³åĽº
    -0.09
    erner
    -0.09
    æ·±åİļ
    -0.09
     Speedway
    -0.09
    trag
    -0.08
    åIJĦ个çݯèĬĤ
    -0.08
    POSITIVE LOGITS
    hel
    0.09
    æĵį
    0.09
    openh
    0.08
    è®©ä½ł
    0.08
    dao
    0.08
    ç®
    0.08
    ban
    0.08
    _numpy
    0.08
     hel
    0.08
    éļĶ
    0.08
    Activations Density 0.100%

    No Known Activations