© 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. 50111
    Prev
    Next
    INDEX
    Explanations

    question words

    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
    ä¸įçŁ¥
    -0.11
    âĨ³
    -0.10
    ä¹ĭ声
    -0.10
    ä¼łè¨Ģ
    -0.09
    untas
    -0.09
    alach
    -0.09
    绪
    -0.09
    æľ¬èº«
    -0.09
    asmus
    -0.09
    .setCharacter
    -0.09
    POSITIVE LOGITS
    åĸ½
    0.10
    åIJĦ个çݯèĬĤ
    0.09
    éĤ£å°±æĺ¯
    0.08
    ä¹Łä¸įæķ¢
    0.08
    ls
    0.08
    Cause
    0.08
    åĩłçĤ¹
    0.08
     dere
    0.08
    åĶĶ
    0.08
    æģķ
    0.08
    Activations Density 0.115%

    No Known Activations