© 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. 61664
    Prev
    Next
    INDEX
    Explanations

    morning news programs

    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
    äºĨåĩł
    -0.11
    ç¬ijç¬ij
    -0.09
    è·
    -0.09
    iets
    -0.09
    åģıåģı
    -0.09
    ä½ľãĤĬ
    -0.09
    hra
    -0.09
    åĩ¹
    -0.08
    äºĨä¸Ģ个
    -0.08
    ograd
    -0.08
    POSITIVE LOGITS
    å¥Ĺè·¯
    0.08
     ÑĩаÑģов
    0.08
    /pm
    0.08
    èµĦ
    0.08
    æĹ¶æ®µ
    0.08
    tek
    0.08
    æĻ¯èī²
    0.08
    åīįåįģ
    0.08
    ä¸ĬåѦ
    0.08
    6
    0.08
    Activations Density 0.011%

    No Known Activations