© 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. 26523
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and cases

    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
    à¸Ĺะ
    -0.10
    å®ĺåı¸
    -0.09
    æĸĩæĺĮ
    -0.09
    ä½łè¯´
    -0.08
    éĶĻè¿ĩ
    -0.08
     tr
    -0.08
    æĴ¥
    -0.08
    髦
    -0.08
    è®®åijĺ
    -0.08
     leaf
    -0.08
    POSITIVE LOGITS
    åĩºå·®
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    ä¾¦æŁ¥
    0.09
     kle
    0.09
     Cham
    0.09
    _VIRTUAL
    0.09
     Sem
    0.08
    ONUS
    0.08
    åįıåĬ©
    0.08
    ç¼ī
    0.08
    Activations Density 0.606%

    No Known Activations