© 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. 3942
    Prev
    Next
    INDEX
    Explanations

    going well or badly

    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
    å¤Ħå¢ĥ
    -0.10
    è¿Ļç§įæĸ¹æ³ķ
    -0.09
    kte
    -0.09
    æĺİæĺİ
    -0.09
    åģļä¸įåĪ°
    -0.09
    ÑĦикÑģ
    -0.09
    åģļ大åģļ强
    -0.09
    CNT
    -0.09
    æķ´ä¸ªäºº
    -0.08
    请æĤ¨
    -0.08
    POSITIVE LOGITS
    åħļé£İ
    0.09
     Gil
    0.09
     Kah
    0.09
    anders
    0.08
    íĻĺ
    0.08
    .chk
    0.08
    积æŀģ
    0.08
    icom
    0.08
    unsch
    0.08
    åĨ²
    0.08
    Activations Density 0.017%

    No Known Activations