© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 34026
    Prev
    Next
    INDEX
    Explanations

    longtime or longstanding

    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
    æĹ¶ä»£çļĦ
    -0.10
    äºĭåħ³
    -0.09
    åĴĮ个人
    -0.09
    å°ıåŃIJ
    -0.09
    çļĦåīįæıIJ
    -0.09
    çļĦæĹ¶åĢĻ
    -0.09
    æĹ¥çĽĬ
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    åħ¨ç¤¾ä¼ļ
    -0.08
    POSITIVE LOGITS
    以ä¾Ĩ
    0.13
    åĽ°æī°
    0.10
    ä¸Ģè´¯
    0.10
    ucher
    0.10
    å·²ä¹ħ
    0.10
    åIJĪä½ľä¼Ļä¼´
    0.10
    -established
    0.09
    以æĿ¥
    0.09
    çĽ¸ä¼ł
    0.09
    -standing
    0.09
    Activations Density 0.009%

    No Known Activations