© 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. 62896
    Prev
    Next
    INDEX
    Explanations

    debut album or first release

    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
    åºŃ
    -0.10
    èĻ
    -0.09
    人äºĭ
    -0.09
    REEN
    -0.09
    èĢĥçĤ¹
    -0.09
    æĬĢæľ¯æĶ¯æĮģ
    -0.09
    çĪ·
    -0.08
    å§Ķå±Ī
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
    å¸¦ä½ł
    -0.08
    POSITIVE LOGITS
    ä¸Ģ款
    0.11
    ä¸Ģæľ¬
    0.10
    æݨåĩºäºĨ
    0.10
    èijĹä½ľ
    0.10
    æݨåĩº
    0.10
    è¿Ļæľ¬ä¹¦
    0.09
    ä¸Ģæľ¬ä¹¦
    0.09
    ä½ľåĵģ
    0.09
    å°ı说
    0.09
     новÑĭй
    0.09
    Activations Density 0.185%

    No Known Activations