© 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. 50185
    Prev
    Next
    INDEX
    Explanations

    why? because

    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
    åķ§
    -0.09
    缴éĢļ车
    -0.09
    沤
    -0.08
    ardy
    -0.08
    ument
    -0.08
     Gren
    -0.08
    oggler
    -0.08
    gren
    -0.08
    ä¹ĥèĩ³
    -0.08
    èĢĮçİ°åľ¨
    -0.08
    POSITIVE LOGITS
    ä¸ļ绩
    0.09
     McInt
    0.08
    æīĵæī°
    0.08
    Úĺ
    0.08
     Belmont
    0.08
     Beckham
    0.08
    壽
    0.08
    _MALLOC
    0.08
    å¿į
    0.08
     Belgium
    0.08
    Activations Density 0.037%

    No Known Activations