© 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. 33619
    Prev
    Next
    INDEX
    Explanations

    on

    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
     Preserve
    -0.09
    åĨħåĪĨæ³Į
    -0.08
    æĥħæĢĢ
    -0.08
    黾
    -0.08
    _counts
    -0.08
    quee
    -0.08
    chu
    -0.08
    prise
    -0.07
     sensit
    -0.07
    æį·
    -0.07
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.11
    æľīæľŁ
    0.10
    çĸµ
    0.10
    æĬĬè¿ĻäºĽ
    0.09
    ogr
    0.09
    wner
    0.09
    olid
    0.09
    æĭĽæĶ¶
    0.09
    æ·Į
    0.09
    èĤļ
    0.09
    Activations Density 0.060%

    No Known Activations