© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    getting tired or fed up

    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
    èµ·åĪĿ
    -0.10
    InitialState
    -0.09
    omba
    -0.09
    çĭŀ
    -0.09
    并ä¸įå¤ļ
    -0.09
    æŀģå°ij
    -0.09
    ä¸įå±ij
    -0.09
    çķ´
    -0.09
    ä¸ĢæĬ¹
    -0.09
     poczÄħtk
    -0.08
    POSITIVE LOGITS
    ä¸įè¦ģåĨį
    0.12
    ä¸įèĥ½åĨį
    0.10
    è¶ĬæĿ¥è¶Ĭ大
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.10
    æĮģç»Ń
    0.09
    enos
    0.09
    ugi
    0.09
    วà¸Ļ
    0.09
    ilos
    0.09
    浪费
    0.09
    Activations Density 0.083%

    No Known Activations