© 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. 34628
    Prev
    Next
    INDEX
    Explanations

    glad to

    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
    æĴ¼
    -0.10
    à¹Į
    -0.09
    eer
    -0.09
    ing
    -0.08
    alc
    -0.08
    noon
    -0.08
    aget
    -0.08
    ä¸Ģä½ĵ
    -0.08
    ivalent
    -0.08
    oret
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    ä¸İåIJ¦
    0.12
    襦
    0.10
    IOUS
    0.10
    itudes
    0.10
    iao
    0.10
    åĿ¨
    0.09
    با
    0.09
     chắn
    0.09
     جدا
    0.09
    Activations Density 0.008%

    No Known Activations