© 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. 11841
    Prev
    Next
    INDEX
    Explanations

    quest, schematic, trait, Soul

    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
    ÑĢÑİ
    -0.10
    åħ¨åľº
    -0.08
    å¦ĤæĦı
    -0.08
    èĮĶ
    -0.08
    åIJ®
    -0.08
     Garr
    -0.08
    azen
    -0.08
    _TRACE
    -0.08
    æľĶ
    -0.08
    æĪĺæľ¯
    -0.08
    POSITIVE LOGITS
     ÑģамÑĭе
    0.10
    kke
    0.10
    ặ
    0.10
    çŀ
    0.09
    ctrine
    0.09
    atedRoute
    0.09
    ëıħ
    0.09
     ÑĢа
    0.09
    criptor
    0.09
    emas
    0.09
    Activations Density 0.018%

    No Known Activations