© 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. 22429
    Prev
    Next
    INDEX
    Explanations

    API services and integrations

    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
    让æ¶Īè´¹èĢħ
    -0.10
    让çĶ¨æĪ·
    -0.10
    åħĪè¡Į
    -0.09
    好ä¸į容æĺĵ
    -0.09
    erge
    -0.09
    åºĶçĶ¨æŁ¥çľĭ
    -0.08
    assed
    -0.08
    使çĶ¨èĢħæĪĸ
    -0.08
    igner
    -0.08
    ŃIJ
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.10
    带åĽŀ
    0.10
    -themed
    0.10
    èĵĦ
    0.09
    _Insert
    0.09
    å¿ĥæĦı
    0.08
    æ¤
    0.08
    é¢ĺæĿIJ
    0.08
     blossom
    0.08
    ä¼ij
    0.08
    Activations Density 1.288%

    No Known Activations