© 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. 9765
    Prev
    Next
    INDEX
    Explanations

    user context

    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
    æ°Ķæ°Ľ
    -0.09
    åĪ°è´¦
    -0.09
    ä¸ĢåŃĹ
    -0.09
    çĴľ
    -0.08
    endon
    -0.08
    æ¼ı
    -0.08
    åĬłæ²¹ç«Ļ
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    ä¸ĢæĹı
    -0.08
    angling
    -0.08
    POSITIVE LOGITS
    çĶ¨æīĭ
    0.11
    涣
    0.11
    æīĭä¸ŃçļĦ
    0.10
    ä¸ľè¥¿
    0.09
    esco
    0.09
    使çĶ¨çļĦ
    0.09
    æĬĢèīº
    0.09
    opers
    0.09
    achine
    0.09
    pecified
    0.08
    Activations Density 0.523%

    No Known Activations