© 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. 52847
    Prev
    Next
    INDEX
    Explanations

    Razor Pages

    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
    æ»ī
    -0.10
    ings
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    amp
    -0.09
    utting
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
    å¹¼ç¨ļ
    -0.08
    éħ¿éħĴ
    -0.08
    ppv
    -0.08
    PropertyParams
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĢ
    0.12
    éĶı
    0.11
    thon
    0.10
    cade
    0.10
    sey
    0.10
    deen
    0.09
    æł·çļĦ
    0.09
    rient
    0.09
    æĪĴ
    0.08
    å³»
    0.08
    Activations Density 0.005%

    No Known Activations