© 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. 32305
    Prev
    Next
    INDEX
    Explanations

    warnings and disclaimers

    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
    çİĭçīĮ
    -0.10
    åĤ¬çĶŁ
    -0.09
    Pont
    -0.09
    åĨĽå®ĺ
    -0.08
    äºĤ
    -0.08
    åħ¶ä¸ŃåĮħæĭ¬
    -0.08
    ç¯Ļ
    -0.08
     Pratt
    -0.08
    欢åij¼
    -0.08
    Dst
    -0.08
    POSITIVE LOGITS
     warned
    0.10
    trag
    0.09
    èѦåijĬ
    0.09
    inel
    0.09
    agate
    0.09
    .Warning
    0.09
    æij©
    0.09
    å¥ī
    0.09
    ÂĢÂ
    0.09
     warning
    0.09
    Activations Density 0.008%

    No Known Activations