© 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. 55768
    Prev
    Next
    INDEX
    Explanations

    search and rescue

    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
    _attached
    -0.09
    èĢį
    -0.09
    æĮĤåı·
    -0.09
    æĺ¥è¿IJ
    -0.09
     воп
    -0.09
    rán
    -0.09
    æIJĵ
    -0.09
    éķ¿éĢĶ
    -0.09
    ä¹ł
    -0.09
     ngu
    -0.08
    POSITIVE LOGITS
    室å¤ĸ
    0.10
    pared
    0.08
    çĬĴ
    0.08
    çĮ·
    0.08
    åIJĮæŶè¿ĺ
    0.08
    ä»įæľª
    0.08
    åıĸåĨ³
    0.08
    仪
    0.08
    ëŁī
    0.08
    ä¸ĩæĪ·
    0.08
    Activations Density 0.026%

    No Known Activations