© 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. 5879
    Prev
    Next
    INDEX
    Explanations

    extend

    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
    ILING
    -0.10
    HING
    -0.09
    iling
    -0.09
    åIJĵ
    -0.08
     clo
    -0.08
     unanim
    -0.08
    _UNDEF
    -0.08
     новÑĭÑħ
    -0.08
    çıı
    -0.07
    æľĢæĸ°
    -0.07
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    ä¸įäºĨ
    0.12
    chn
    0.10
    à¸Ŀ
    0.10
     StObject
    0.10
    侪
    0.09
    reich
    0.09
    OrCreate
    0.09
    ä¸ĸ代
    0.09
    å®ĮåĸĦ
    0.09
    Activations Density 0.040%

    No Known Activations