© 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. 50216
    Prev
    Next
    INDEX
    Explanations

    how are you

    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
    çĥ
    -0.10
    èµ°åĩºåİ»
    -0.09
    çĶŁåij½åĬĽ
    -0.09
    é»ijå¤ľ
    -0.09
    没äºĭ
    -0.09
    æŀģèĩ´
    -0.08
     кÑĢови
    -0.08
    estro
    -0.08
    èĿ¶
    -0.08
    çľĭä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    olls
    0.10
    apes
    0.09
    èĤ¥
    0.09
    è¿Ļæĸ¹éĿ¢
    0.09
    æ¯ĵ
    0.09
    è§ļ
    0.08
     ç¬
    0.08
    existent
    0.08
    åĨ³æĪĺ
    0.08
    findOne
    0.08
    Activations Density 0.013%

    No Known Activations