© 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. 54328
    Prev
    Next
    INDEX
    Explanations

    names ending in -ico

    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
    äºĨä¸Ģæī¹
    -0.09
    eping
    -0.09
    hammer
    -0.09
    ame
    -0.09
    kie
    -0.08
    _overflow
    -0.08
    æĸĽ
    -0.08
    locker
    -0.08
    cheid
    -0.08
    ä¸Ģä½ĵ
    -0.08
    POSITIVE LOGITS
    褶
    0.09
     Bett
    0.09
    éĶ£
    0.09
    çļĦçľ¼çĿĽ
    0.08
    éŨæĪ·ç½ijç«Ļ
    0.08
    寨
    0.08
    Ī
    0.08
    uts
    0.08
    åŁļ
    0.08
     Stef
    0.08
    Activations Density 0.003%

    No Known Activations