© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37984
    Prev
    Next
    INDEX
    Explanations

    in the presence of

    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±İ
    -0.09
    ä»
    -0.09
    èĥ½å¤Łåľ¨
    -0.09
    apur
    -0.09
    ä¸Ģ代
    -0.09
    aster
    -0.08
    èįĶæŀĿ
    -0.08
     Friedman
    -0.08
    ics
    -0.08
    åIJIJ
    -0.08
    POSITIVE LOGITS
     Ñĥказан
    0.09
     же
    0.09
    åīįè¿°
    0.09
    казан
    0.09
     mismo
    0.09
     inversion
    0.08
     aforementioned
    0.08
    èĩªæľī
    0.08
    åĨ¬å¥¥
    0.08
    è·Łè¿Ľ
    0.08
    Activations Density 0.054%

    No Known Activations