© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32637
    Prev
    Next
    INDEX
    Explanations

    speaking to reporters

    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
    ç©¶
    -0.10
    edium
    -0.10
    éĤ£åĦ¿
    -0.09
    å¨ĥ
    -0.09
    ewing
    -0.09
    è·Ľ
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    å°±ç»Ļ大家
    -0.09
    åı¸
    -0.09
    满äºĨ
    -0.09
    POSITIVE LOGITS
    zan
    0.09
    LOCKS
    0.09
    è§ģéĿ¢
    0.09
    è°ı
    0.09
    /vendors
    0.08
    è¿ĺä¸įå¦Ĥ
    0.08
    触åıĬ
    0.08
    å¼ĢäºĨ
    0.08
    _float
    0.08
    uby
    0.07
    Activations Density 0.009%

    No Known Activations