© 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. 2587
    Prev
    Next
    INDEX
    Explanations

    transience or temporary states

    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
    æľªæĽ¾
    -0.10
    å¼Ģåħĥ
    -0.10
    olec
    -0.10
    æŁ¬
    -0.10
    åľĥ
    -0.09
    uries
    -0.09
    éĹ°
    -0.09
    æĪIJç«ĭ以æĿ¥
    -0.09
    è¾Ł
    -0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.09
    POSITIVE LOGITS
    çŁŃæļĤ
    0.23
    临æŶ
    0.23
     temporary
    0.20
     fleeting
    0.19
    æĺĻ
    0.19
    temporary
    0.17
     ephem
    0.17
     transient
    0.17
     Temporary
    0.16
    Transient
    0.16
    Activations Density 0.302%

    No Known Activations