© 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. 19534
    Prev
    Next
    INDEX
    Explanations

    brand new

    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
    èŀ³
    -0.09
    BOR
    -0.09
    ALSE
    -0.09
    ORB
    -0.09
    erator
    -0.08
    erty
    -0.08
    çĺ´
    -0.08
    åł¡åŀĴ
    -0.08
    orical
    -0.08
    âĤ½
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.11
    irectional
    0.10
    vice
    0.10
    less
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    ä¸Ģ头
    0.09
    หมà¸Ķ
    0.09
    обÑĢа
    0.09
    ä¸įéĹ´
    0.09
    anded
    0.09
    Activations Density 0.009%

    No Known Activations