© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19788
    Prev
    Next
    INDEX
    Explanations

    scientific terminology suffixes

    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
    èĵŁ
    -0.12
    ç´§åĩij
    -0.09
    âĪ
    -0.09
    为æĤ¨æıIJä¾Ľ
    -0.09
     levy
    -0.08
    æ¨Ł
    -0.08
    ERAL
    -0.08
    Bulk
    -0.08
    ä»ĵåĤ¨
    -0.08
    å³Ĵ
    -0.08
    POSITIVE LOGITS
    æ·±åĪĩ
    0.12
    çľĩ
    0.10
    æ²»
    0.09
    è£
    0.09
    追赶
    0.09
    åIJŀ
    0.09
    åĨ¥
    0.09
    bench
    0.08
     OnCollision
    0.08
    æĿ¿åĿĹ
    0.08
    Activations Density 0.060%

    No Known Activations