© 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. 6534
    Prev
    Next
    INDEX
    Explanations

    all the way

    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
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.08
    æĹłæĥħ
    -0.08
    unknown
    -0.08
     others
    -0.08
    æľīçĽĬ
    -0.08
    è¿İ
    -0.08
    çľ¼åīįçļĦ
    -0.08
    bie
    -0.08
     Wo
    -0.08
     formulate
    -0.08
    POSITIVE LOGITS
    åĪ°çİ°åľ¨
    0.10
    赶åĪ°
    0.10
    涧
    0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.09
    å½»
    0.09
     меÑħаниз
    0.09
    åħļåĴĮ
    0.09
    ä¸Ģ缴åĪ°
    0.09
    æ·¦
    0.09
    LOPT
    0.09
    Activations Density 0.030%

    No Known Activations