© 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. 61666
    Prev
    Next
    INDEX
    Explanations

    reunion or unite

    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
    tober
    -0.12
    asu
    -0.09
    åĽŀäºĭ
    -0.09
    ITT
    -0.09
    obi
    -0.09
    аÑĪ
    -0.09
    kre
    -0.08
    çķĮçļĦ
    -0.08
    mens
    -0.08
    iba
    -0.08
    POSITIVE LOGITS
     STATS
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    æĥħ人
    0.09
    åĪ°æĿ¥
    0.09
    åĴĮåıijå±ķ
    0.09
    éĺĶ
    0.09
    åĴª
    0.09
    icher
    0.09
    ivan
    0.08
    nqu
    0.08
    Activations Density 0.008%

    No Known Activations