© 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. 49370
    Prev
    Next
    INDEX
    Explanations

    specific or certain qualifiers

    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
    åIJij社ä¼ļ
    -0.10
    lobs
    -0.09
    æ¶īåıĬ
    -0.09
    åºı
    -0.09
    å«£
    -0.09
    .Cast
    -0.09
    å®ŀæĸ½ç»ĨåĪĻ
    -0.09
    egl
    -0.08
    EDIA
    -0.08
    åĪ¶åĵģ
    -0.08
    POSITIVE LOGITS
     certain
    0.30
    çī¹å®ļ
    0.30
     Certain
    0.27
    Certain
    0.25
    ä¸Ģå®ļçļĦ
    0.23
    æŁIJäºĽ
    0.23
     specific
    0.23
     bestimm
    0.23
     particular
    0.22
    ä¸Ģå®ļ
    0.21
    Activations Density 0.363%

    No Known Activations