© 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. 51617
    Prev
    Next
    INDEX
    Explanations

    more ... than

    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
    éĿŀ常çļĦ
    -0.10
    ä¿Ĺ称
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    iq
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.08
    ä¸ĢæŶ
    -0.08
    åįģåĪĨ
    -0.08
    éļıæīĭ
    -0.08
    举æŃ¢
    -0.08
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    OSE
    0.11
    好åIJ§
    0.10
    /from
    0.10
    çħ
    0.09
    entr
    0.09
    جاÙħ
    0.09
    mani
    0.09
    _markers
    0.09
    æµĵåİļ
    0.09
    alic
    0.08
    Activations Density 0.012%

    No Known Activations