© 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. 56640
    Prev
    Next
    INDEX
    Explanations

    price or currency values

    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
    åıijçİ°èĩªå·±
    -0.09
    ä¾Ľ
    -0.09
     mong
    -0.08
    å°ıä¼Ļ伴们
    -0.08
    ouro
    -0.08
    éķ¿çŁŃ
    -0.08
    еÑģÑĮ
    -0.08
    èĭ¦
    -0.08
    æıŃéľ²
    -0.08
    è¿ĩåī©
    -0.08
    POSITIVE LOGITS
    ç¾İ
    0.11
    orz
    0.10
     ÑĢей
    0.09
    öl
    0.09
    favor
    0.09
    ä»·ä½į
    0.09
    ewing
    0.08
    _dx
    0.08
    PRICE
    0.08
    acked
    0.08
    Activations Density 0.176%

    No Known Activations