© 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. 1653
    Prev
    Next
    INDEX
    Explanations

    fine, but, enough, blame, wait

    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
    åºĶä»ĺ
    -0.09
    çĽijçĿ£ç®¡çIJĨ
    -0.09
    æ³Ľ
    -0.08
    åİĮæģ¶
    -0.08
    åİĮ
    -0.08
     superv
    -0.08
    èħ»
    -0.08
     GUID
    -0.08
    æĢĻ
    -0.07
    åıįåĩ»
    -0.07
    POSITIVE LOGITS
    å°Ĭéĩį
    0.15
    æĶ¾è¿ĩ
    0.13
    ä¸įåİ»
    0.12
    人家
    0.12
    榴
    0.11
    æĶ¾æīĭ
    0.11
    ä¹Łä¸įæķ¢
    0.10
    å°Ĭ
    0.10
    æīĵæī°
    0.10
    imeline
    0.10
    Activations Density 0.050%

    No Known Activations