© 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. 18395
    Prev
    Next
    INDEX
    Explanations

    US states and their sports teams

    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
    èĬ¥
    -0.09
    缴æݥ影åĵį
    -0.09
    åħ¨åĽ½
    -0.08
    çŃIJ
    -0.08
    æĤĮ
    -0.08
    åĨįæĿ¥
    -0.08
    åįģåŃĹ
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    cial
    -0.07
    æľ¬åħ¬åı¸
    -0.07
    POSITIVE LOGITS
    漪
    0.12
    æį§
    0.10
    çĶµåĻ¨
    0.09
    Canceled
    0.09
    æłĭ
    0.09
    æİĮ
    0.09
     pole
    0.09
    éĩijéĵ¶
    0.09
    _CHAN
    0.09
    森æŀĹ
    0.09
    Activations Density 0.018%

    No Known Activations