© 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. 50799
    Prev
    Next
    INDEX
    Explanations

    mimic, learn, example, inspiration

    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
    umper
    -0.09
     compreh
    -0.09
    订
    -0.09
    .rs
    -0.09
     dese
    -0.08
    ortho
    -0.08
    åįĴ
    -0.08
    otty
    -0.08
    ursed
    -0.08
    raz
    -0.08
    POSITIVE LOGITS
    åĢŁéī´
    0.26
    模仿
    0.17
    åIJ¸åıĸ
    0.16
    æ¦ľæł·
    0.15
     inspiration
    0.13
    æ±²åıĸ
    0.13
     lessons
    0.13
    åIJ¸æĶ¶
    0.13
    仿
    0.13
    Insp
    0.12
    Activations Density 0.068%

    No Known Activations