© 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. 56860
    Prev
    Next
    INDEX
    Explanations

    confirmation and validation

    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
    iders
    -0.09
    estate
    -0.09
    æ¤İ
    -0.09
    itters
    -0.09
     vra
    -0.08
    uder
    -0.08
     возможно
    -0.08
    ested
    -0.08
    æ¤į
    -0.08
    ÙĨÙĪ
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    åĴĮæĶ¯æĮģ
    0.11
     suspicions
    0.10
    çİ°è¡Į
    0.10
    åį°
    0.09
    å·©åĽº
    0.09
    è¯ģå®ŀ
    0.09
    åªĴ
    0.09
    äºĨæĪijçļĦ
    0.09
    CHO
    0.09
    Activations Density 0.041%

    No Known Activations