© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    funny thing, funny enough, funny web

    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
    amp
    -0.10
    itel
    -0.10
    aan
    -0.10
    ives
    -0.10
    igator
    -0.09
    责任åĪ¶
    -0.09
    主è¦ģåĨħ容
    -0.09
    ually
    -0.09
    åı¯èĥ½æĢ§
    -0.09
    mium
    -0.09
    POSITIVE LOGITS
    -looking
    0.12
    NEL
    0.10
    اÙħÙĦ
    0.10
    tics
    0.09
    äºĽ
    0.09
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    0.09
    keiten
    0.09
    деÑģÑıÑĤ
    0.09
    twig
    0.08
    Åķ
    0.08
    Activations Density 0.008%

    No Known Activations