© 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. 23863
    Prev
    Next
    INDEX
    Explanations

    NAS and clustering

    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
    æĬijåĪ¶
    -0.08
    ä¹ĺåĿIJ
    -0.08
    èĪ·
    -0.08
     Yas
    -0.07
     Zuk
    -0.07
    mez
    -0.07
     Brass
    -0.07
    èĩªç§°
    -0.07
     Campaign
    -0.07
     ÑĢом
    -0.07
    POSITIVE LOGITS
    ä¸Ģä½ĵ
    0.11
    æĭ¼éŁ³
    0.11
    骷
    0.10
    lude
    0.10
    çģ«çĥ§
    0.10
    èĶº
    0.10
    åĩłçĤ¹
    0.10
    çŀ¿
    0.10
    ä¸įåĩº
    0.10
    è°
    0.10
    Activations Density 0.135%

    No Known Activations