© 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. 17790
    Prev
    Next
    INDEX
    Explanations

    exam questions

    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
    详
    -0.09
    æ°´æºIJ
    -0.09
    æĭĽ
    -0.09
    æĪĸå°Ĩ
    -0.08
    æIJ¬åĪ°
    -0.08
     nod
    -0.08
    çĶ·å¥³
    -0.08
    çIJ¶
    -0.08
    æķĻèģĮå·¥
    -0.08
    åįĹæĸ¹
    -0.08
    POSITIVE LOGITS
    _questions
    0.10
    èĢĥçĶŁ
    0.09
    çĩĥæ²¹
    0.09
    åŀĤ
    0.08
     questions
    0.08
     prep
    0.08
     Exam
    0.08
    å¤ĩèĢĥ
    0.08
    æī§ä¸ļ
    0.08
     Authorized
    0.08
    Activations Density 0.093%

    No Known Activations