© 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. 56676
    Prev
    Next
    INDEX
    Explanations

    time expressions with "of" or "after"

    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
    åľ¨è¿Ļ
    -0.09
    èģĶ社
    -0.08
    asers
    -0.08
    lint
    -0.08
    æĥ³æĥ³
    -0.08
    ç¦Ħ
    -0.08
    å°±æľī
    -0.08
    åľ¨è¿Ļ个
    -0.08
    ksen
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    POSITIVE LOGITS
     they
    0.12
     you
    0.11
    æĪĸå¤ļ
    0.11
     we
    0.10
    åħ¶
    0.10
    ä½łä¸į
    0.10
    ä»ĸ们
    0.09
     someone
    0.09
     it
    0.09
    ä½łåľ¨
    0.09
    Activations Density 0.034%

    No Known Activations