© 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. 34144
    Prev
    Next
    INDEX
    Explanations

    in the world

    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
    alo
    -0.11
    çĺ´
    -0.09
    ipse
    -0.08
    ione
    -0.08
    aul
    -0.08
    HING
    -0.08
    YST
    -0.08
    -lo
    -0.08
    ovah
    -0.08
     ìĤ´ìķĦ
    -0.08
    POSITIVE LOGITS
    天ä¸ĭ
    0.12
     миÑĢа
    0.10
    ág
    0.10
    uos
    0.09
    ä¹ł
    0.09
    æķ´åĢĭ
    0.09
    æķ´ä¸ª
    0.09
    鸾
    0.09
    æĬĴ
    0.09
    _fx
    0.08
    Activations Density 0.078%

    No Known Activations