© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19867
    Prev
    Next
    INDEX
    Explanations

    retro and retroviral

    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
    oret
    -0.09
    æĸ°çļĦ
    -0.08
    orem
    -0.08
    oretical
    -0.08
    inese
    -0.08
    ings
    -0.08
    EPS
    -0.08
    æѤåĪ»
    -0.07
    autop
    -0.07
    ãģĹãģ¾ãģĨ
    -0.07
    POSITIVE LOGITS
    -minded
    0.13
    å®ļäºĨ
    0.11
    æĢ§å¼º
    0.10
    land
    0.10
    pectives
    0.10
    avl
    0.10
    讳
    0.09
    ize
    0.09
    gression
    0.09
    ä¼ļå±ķä¸Ńå¿ĥ
    0.09
    Activations Density 0.017%

    No Known Activations