© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19784
    Prev
    Next
    INDEX
    Explanations

    whether or and other

    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
    .gradient
    -0.09
    åħīèį£
    -0.09
    serter
    -0.09
    åħį
    -0.09
     Diamond
    -0.09
    泡
    -0.08
    zew
    -0.08
    æĬ¥
    -0.08
    ByVersion
    -0.08
    ordin
    -0.08
    POSITIVE LOGITS
    æĹłè®º
    0.11
    åıªè¦ģæľī
    0.10
     whatsoever
    0.10
    çĦ¡è«ĸ
    0.09
    åıªè¦ģä½ł
    0.09
    ä»»ä½ķ
    0.09
    åĽ½åĨħå¤ĸ
    0.09
    ä¸Ŀ毫ä¸į
    0.09
    åı¤äºº
    0.09
    æĹłè®ºæĺ¯
    0.09
    Activations Density 0.079%

    No Known Activations