© 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. 10366
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/verb

    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
    人家
    -0.08
    è¯Ģ
    -0.08
    æ³Į
    -0.08
    ìħĪ
    -0.08
    æĻ°
    -0.08
    åĿıäºĭ
    -0.08
    vironment
    -0.08
    สะ
    -0.08
    æ±Ĺ
    -0.08
    ç¼ij
    -0.07
    POSITIVE LOGITS
    acia
    0.09
    çİŁ
    0.09
    æĶ¾è¿ĩ
    0.09
    è¯Ĥ
    0.08
    ä¹ĥèĩ³
    0.08
    è¿ĻèĪ¬
    0.08
    ØŃج
    0.08
    beits
    0.08
    ä¸Ģçķª
    0.08
    礴
    0.08
    Activations Density 0.584%

    No Known Activations