© 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. 31321
    Prev
    Next
    INDEX
    Explanations

    turned to / upside down

    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
    åĨĴçĿĢ
    -0.09
    éĥģ
    -0.09
    éħįå¥Ĺ
    -0.09
    ipple
    -0.08
    REMOTE
    -0.08
    æĭ¿åĩº
    -0.08
    饶
    -0.08
    amine
    -0.08
    egral
    -0.08
    åıĺçİ°
    -0.08
    POSITIVE LOGITS
    лÑĮн
    0.09
    ç±
    0.09
    éŃĶ鬼
    0.08
    å®Įåħ¨ä¸įåIJĮ
    0.08
    ustria
    0.08
    åĴ½åĸī
    0.08
    对ä¸ŃåĽ½
    0.08
     krist
    0.08
    æĭ¥æĬ±
    0.08
    éric
    0.08
    Activations Density 0.150%

    No Known Activations