© 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. 55356
    Prev
    Next
    INDEX
    Explanations

    theory to practice

    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
    æ¸ł
    -0.09
     Alternate
    -0.09
    宸
    -0.09
    件äºĭ
    -0.08
    ä¸Ģäºĭ
    -0.08
    ç©´ä½į
    -0.08
    ä¿Ŀä½ı
    -0.08
    沤
    -0.08
    åķ
    -0.08
    ernel
    -0.08
    POSITIVE LOGITS
    å®ŀè·µä¸Ń
    0.22
    å®ŀè·µ
    0.21
    å®ŀéĻħ
    0.19
    çļĦå®ŀéĻħ
    0.18
     practical
    0.17
     practice
    0.17
    å®ŀéĻħæĥħåĨµ
    0.16
     prakt
    0.15
    å®ŀè·µç»ıéªĮ
    0.14
    å®ŀåĬ¡
    0.14
    Activations Density 0.073%

    No Known Activations