© 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. 31498
    Prev
    Next
    INDEX
    Explanations

    rebellious political punk attitude

    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
    çIJĨäºĭ
    -0.09
    æĤ²ä¼¤
    -0.08
     Sang
    -0.08
    å¾Īæ·±
    -0.08
    æģĭ
    -0.08
    çݯç»ķ
    -0.08
    çIJĽ
    -0.08
    ç½ij讯
    -0.08
    /*@
    -0.08
    getc
    -0.08
    POSITIVE LOGITS
    é¢łè¦Ĩ
    0.10
    æĸ¥
    0.09
    eph
    0.09
    ecz
    0.09
    ored
    0.09
    éĴĪ
    0.09
     radical
    0.09
    FDA
    0.08
    erties
    0.08
    积æŀģéħįåIJĪ
    0.08
    Activations Density 0.184%

    No Known Activations