© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    condensation

    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
    é³Į
    -0.09
    CAA
    -0.09
    ç±į
    -0.09
    lij
    -0.08
    éĢĢ
    -0.08
    大声
    -0.08
    ä»ĸ说
    -0.08
    ovation
    -0.08
    keys
    -0.08
     outr
    -0.08
    POSITIVE LOGITS
    æįķæįī
    0.12
    æĶ¶éĽĨ
    0.12
    æįķ
    0.10
    æIJľéĽĨ
    0.10
    ä¸ĭä¾Ĩ
    0.09
    æĭ¦æĪª
    0.09
    罩
    0.09
     cond
    0.09
     interception
    0.09
    åIJ¸åıĸ
    0.09
    Activations Density 0.104%

    No Known Activations