© 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. 53885
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania, Heart of Midlothian, immune system, check FAQ

    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
    éªı
    -0.09
    ecal
    -0.09
    è´²
    -0.08
    IU
    -0.08
    羣æŃ£çļĦ
    -0.08
    ä¸ģ
    -0.08
    æŁĦ
    -0.08
    çīµ
    -0.08
    çī
    -0.08
    tran
    -0.08
    POSITIVE LOGITS
    æ®ĸ
    0.09
    é¦ĭ
    0.09
    .nasa
    0.08
    ä¸įèĩ³äºİ
    0.08
    ataka
    0.08
    illet
    0.08
    peare
    0.08
     пÑĢог
    0.08
    ãĤ
    0.08
    è¿ĺ以为
    0.08
    Activations Density 0.428%

    No Known Activations