© 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. 39711
    Prev
    Next
    INDEX
    Explanations

    know of X

    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
    /or
    -0.10
    åij·
    -0.09
    eri
    -0.09
    alus
    -0.09
    ymm
    -0.09
    istes
    -0.09
    夫
    -0.09
    chez
    -0.09
    fmt
    -0.08
    éri
    -0.08
    POSITIVE LOGITS
    eks
    0.09
    èįŀ
    0.09
    è¿ĻçĤ¹
    0.09
    ä¸Ģæłĭ
    0.09
    é¢ģå¸ĥ
    0.09
    ÑĤи
    0.09
    æīĢ产çĶŁçļĦ
    0.09
    /about
    0.08
    åīįæīĢ
    0.08
    åIJĦç§į
    0.08
    Activations Density 0.058%

    No Known Activations