© 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. 57049
    Prev
    Next
    INDEX
    Explanations

    python, : ==, Inquiry, Gold

    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
    èĨº
    -0.09
    äºĭä¸ļåıijå±ķ
    -0.09
    âĸ¢
    -0.09
    defgroup
    -0.09
    iral
    -0.09
    å±ıéļľ
    -0.09
    æĹĦ
    -0.08
    æĮĸæİĺ
    -0.08
    æĪijåıªæĺ¯
    -0.08
     ÑģÑĤо
    -0.08
    POSITIVE LOGITS
    полÑĮ
    0.09
    çģ«åĬĽ
    0.08
    èī°å·¨
    0.08
    èĤīä½ĵ
    0.08
    å¢ĥåĨħ
    0.08
    å°ıå§IJ
    0.08
    Ñģлав
    0.08
    ModelIndex
    0.08
    nesc
    0.08
    .itemView
    0.08
    Activations Density 0.002%

    No Known Activations