© 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. 21735
    Prev
    Next
    INDEX
    Explanations

    past tense verbs in research contexts

    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
    ç¾ŀ
    -0.11
    æĺ¯ä¸Ģä½į
    -0.09
    iglia
    -0.09
    ookie
    -0.09
    æľī人说
    -0.09
    交代
    -0.08
    è¾Ł
    -0.08
    éĢŁåº¦å¿«
    -0.08
    wÅĤ
    -0.08
    AFX
    -0.08
    POSITIVE LOGITS
    èĥį
    0.10
    ä¸Ģç³»åĪĹ
    0.09
    åĴ©
    0.09
    éĥ½æ²¡
    0.09
    æī¬
    0.09
    åĩ¼
    0.09
    åħģ许
    0.08
    å®´ä¼ļ
    0.08
    褶
    0.08
    èµŀ
    0.08
    Activations Density 0.473%

    No Known Activations