© 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. 63361
    Prev
    Next
    INDEX
    Explanations

    not that / not so

    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
    èĻ¬
    -0.10
    ä¸ĢåĪĩ
    -0.09
    趴
    -0.09
    éĴ»çłĶ
    -0.09
    ä½łèĥ½
    -0.08
    ä»»ä½ķ
    -0.08
     vid
    -0.08
    ä»ĸ们ä¼ļ
    -0.08
    _RESOURCES
    -0.08
    arios
    -0.08
    POSITIVE LOGITS
    并ä¸įæĺ¯å¾Ī
    0.13
    ä¸į太好
    0.13
    çĶļ
    0.13
    è¾ĥå¤ļ
    0.12
    ä¸į太
    0.12
    æ¯Ķè¾ĥå¤ļ
    0.11
    ä¸įæĺ¯å¾Ī
    0.11
    ãģĤãģ¾ãĤĬ
    0.11
    ä¸įå¤ļ
    0.11
    å¾Īæĺ¯
    0.10
    Activations Density 0.104%

    No Known Activations