© 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. 19411
    Prev
    Next
    INDEX
    Explanations

    fulfillment, allegorical, meaning, ultimate

    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
    å°Ĭ严
    -0.10
    еÑģÑģ
    -0.09
    æĶ¾æīĭ
    -0.08
    åĴ¬
    -0.08
    估计
    -0.08
    æij¸
    -0.08
    oley
    -0.08
    åıĹ访
    -0.08
    atas
    -0.08
     bla
    -0.08
    POSITIVE LOGITS
    äºĴè¡¥
    0.10
    åĸ»
    0.10
    æĸ°éĻĪ代谢
    0.10
     alleg
    0.10
    ieren
    0.09
    BufferData
    0.09
     rer
    0.09
    åħ½
    0.09
    è§ĦåĪĴ建设
    0.09
    浡
    0.09
    Activations Density 0.050%

    No Known Activations