© 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. 53705
    Prev
    Next
    INDEX
    Explanations

    video game titles

    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
    æĮĩçĶ²
    -0.09
    emotion
    -0.09
    _unused
    -0.08
     Sak
    -0.08
    ushi
    -0.08
    å·¡æŁ¥
    -0.08
    女åŃIJ
    -0.08
    æĥħ绪
    -0.08
    Ñĥгл
    -0.08
    xy
    -0.08
    POSITIVE LOGITS
    éĥİ
    0.11
    ä¸ĵ项è¡ĮåĬ¨
    0.09
    ä¸ĢéĹ´
    0.09
    è´
    0.09
    åĭ¤
    0.09
    ç²ľ
    0.08
    alla
    0.08
    åĬ¼
    0.08
    姣
    0.08
    Counts
    0.08
    Activations Density 0.007%

    No Known Activations