© 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. 49573
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
    å®ŀè·µä¸Ń
    -0.10
    unity
    -0.09
    å¤ĸåĩº
    -0.09
    _xx
    -0.09
    è¿Ļ对
    -0.09
    ERC
    -0.09
    andle
    -0.09
    POOL
    -0.09
     ECC
    -0.09
    /java
    -0.08
    POSITIVE LOGITS
    碴
    0.09
    -than
    0.08
    袤
    0.08
     Enforcement
    0.08
    å¼Ń
    0.08
    è½
    0.08
    åĦ¿
    0.08
    Ñģп
    0.08
    ä¿©
    0.07
    venes
    0.07
    Activations Density 1.108%

    No Known Activations