© 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. 30374
    Prev
    Next
    INDEX
    Explanations

    prepositions introducing 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
    æŃ£æĸĩ
    -0.10
    å°±è·Ł
    -0.09
    âİ
    -0.08
    çłĿ
    -0.08
    æİīäºĨ
    -0.08
    建设åĴĮ
    -0.08
    åij¼åĴĮ
    -0.07
    ople
    -0.07
    æ¬Ħ
    -0.07
    esc
    -0.07
    POSITIVE LOGITS
     thereof
    0.09
    /or
    0.09
    çŃīåİŁåĽł
    0.09
    æĹłæķ°æ¬¡
    0.09
    rog
    0.09
    ence
    0.09
    _fac
    0.08
    ä¸į失
    0.08
    cá
    0.08
    ::__
    0.08
    Activations Density 0.121%

    No Known Activations