© 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. 62161
    Prev
    Next
    INDEX
    Explanations

    legal or justification terms

    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
    梵
    -0.08
     Eden
    -0.08
    ë°°
    -0.08
     flam
    -0.08
    ipher
    -0.08
    å¾Ī好
    -0.08
    оде
    -0.08
    (Optional
    -0.08
    éħį
    -0.07
     caucus
    -0.07
    POSITIVE LOGITS
    ено
    0.11
    å°±æĺ¯è¦ģ
    0.10
    åIJ¦åĪĻ
    0.09
    ä¸ĢçĶŁ
    0.09
    å®ł
    0.09
    ä¹Łè¦ģ
    0.09
    ä¿Ŀå®Ī
    0.09
    æıĨ
    0.08
    åIJ¦åīĩ
    0.08
    iest
    0.08
    Activations Density 0.034%

    No Known Activations