© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    question/answer format

    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
    é¢ĦåijĬ
    -0.09
    æĶ¯éħį
    -0.08
    ä»İå°ı
    -0.08
    认è´Ń
    -0.08
    æķ²
    -0.08
    æįIJèµł
    -0.08
    amen
    -0.08
    ä¸Ģ段
    -0.08
     Perr
    -0.08
    çļĦä¸Ģ大
    -0.07
    POSITIVE LOGITS
     ëĭµë³Ģ
    0.14
    åĽŀçŃĶ
    0.14
    è¿Ļ个éĹ®é¢ĺ
    0.14
    çļĦåĽŀçŃĶ
    0.12
    é¢ĺ主
    0.12
    éĹ®çŃĶ
    0.11
    解çŃĶ
    0.11
     answered
    0.11
    .answer
    0.11
    çŃĶå¤į
    0.11
    Activations Density 0.102%

    No Known Activations