© 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. 63017
    Prev
    Next
    INDEX
    Explanations

    and state

    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
    åĴĮå®ĮåĸĦ
    -0.11
    建设åĴĮ
    -0.09
    éļıæŶ
    -0.08
    åĴĮå°ļ
    -0.08
    åĴĮåıijå±ķ
    -0.08
    å¾Ĺå¾Ī
    -0.08
    çĶŁäº§åĴĮ
    -0.08
    æĪijåĴĮ
    -0.08
    çĶļ
    -0.08
    æIJº
    -0.08
    POSITIVE LOGITS
    /or
    0.12
    rogen
    0.11
    2
    0.11
    9
    0.10
    å¤ļãģı
    0.09
    erto
    0.09
    ãģıãĤĵ
    0.09
    7
    0.09
     breve
    0.09
    0
    0.09
    Activations Density 0.191%

    No Known Activations