© 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. 11852
    Prev
    Next
    INDEX
    Explanations

    brown

    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
    çĸĨ
    -0.11
    èįī
    -0.10
    sut
    -0.10
    åĴĴ
    -0.10
    å¸ħåĵ¥
    -0.09
    æĭĬ
    -0.09
    æŀľ
    -0.09
    illis
    -0.09
    ibe
    -0.09
    åĢ®
    -0.09
    POSITIVE LOGITS
    éĿ¢çĽ®
    0.10
    edom
    0.09
    åIJ¸æĶ¶
    0.09
    æ¯ıå¹´éĥ½
    0.08
    -eyed
    0.08
    çĿ
    0.08
    ish
    0.08
    _deg
    0.08
    åIJ¸
    0.08
    à¹Ĩ
    0.08
    Activations Density 0.007%

    No Known Activations