© 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. 57552
    Prev
    Next
    INDEX
    Explanations

    MEMS and liquid crystal displays

    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
    èµ°è¿ij
    -0.10
    åĬłæ·±
    -0.09
    æģª
    -0.09
    éºĴéºŁ
    -0.09
    INTERNAL
    -0.09
    éĶĻäºĨ
    -0.09
    çŀĢ
    -0.09
    æ·¹
    -0.09
    ıt
    -0.09
    ç¬ij声
    -0.09
    POSITIVE LOGITS
    祼
    0.09
    çĵ·
    0.09
    èĬĴ
    0.08
    注åĨĮèµĦæľ¬
    0.08
    æľīæĦı
    0.08
     Hull
    0.08
     Mong
    0.08
    onto
    0.08
    åŀ¢
    0.08
    éĥ¨
    0.08
    Activations Density 0.300%

    No Known Activations