© 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. 5940
    Prev
    Next
    INDEX
    Explanations

    within a time period

    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
    alic
    -0.10
    请åıĬæŶ
    -0.08
    å²IJ
    -0.08
    gee
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    ishi
    -0.08
    _Null
    -0.08
    æĹłè®º
    -0.08
    åĨįåĪ°
    -0.08
    å·¡åĽŀ
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.12
    çļĦæŶéĹ´éĩĮ
    0.11
    å´ĩé«ĺ
    0.10
    æĥ³å¿µ
    0.09
    bilt
    0.09
    ä¸Ģå®ļç¨ĭ度
    0.09
    ä¿İ
    0.09
    nob
    0.09
    åĩłå¤©
    0.08
    åĩłå¹´
    0.08
    Activations Density 0.017%

    No Known Activations