© 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. 33329
    Prev
    Next
    INDEX
    Explanations

    notice and warning

    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
    uela
    -0.09
     trÆ°ng
    -0.09
    hower
    -0.09
    éĺŁéķ¿
    -0.09
    _rd
    -0.09
    åŁ¹
    -0.09
    ué
    -0.09
    ë©ľ
    -0.08
    æľĢ容æĺĵ
    -0.08
    .trace
    -0.08
    POSITIVE LOGITS
    ÅĦ
    0.08
    åĩºç¤º
    0.08
    为æĤ¨
    0.08
    epy
    0.08
    ç©į
    0.08
    积
    0.08
    æĤĦçĦ¶
    0.08
    ä¼łç»Łäº§ä¸ļ
    0.08
    è§Ħ模以ä¸Ĭ
    0.08
    åĮºåŁŁåĨħ
    0.08
    Activations Density 0.002%

    No Known Activations