© 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. 49171
    Prev
    Next
    INDEX
    Explanations

    quote marks

    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
    /***/
    -0.08
    duction
    -0.08
    æµģåĬ¨
    -0.08
    unded
    -0.08
    clave
    -0.08
    èĵ¬
    -0.08
    羣å®ŀ
    -0.08
    éĹ¨æ§Ľ
    -0.08
    Marshal
    -0.08
    ãĢ
    -0.08
    POSITIVE LOGITS
    毫ä¸įçĬ¹è±«
    0.10
    å¼Ģåĩº
    0.10
    çļĦä¸ĢéĿ¢
    0.10
    åįģæĿ¡
    0.09
    åħ»æĪIJ
    0.09
     araç
    0.09
    addtogroup
    0.09
    нал
    0.09
    æĢª
    0.08
    éļıæīĭ
    0.08
    Activations Density 0.005%

    No Known Activations