© 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. 21723
    Prev
    Next
    INDEX
    Explanations

    considering or thinking about future actions

    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
    带æĿ¥çļĦ
    -0.09
    ä¸ĢæŦ
    -0.08
    å«ī
    -0.08
    æĬ¬
    -0.08
    æĿ¥åĽŀ
    -0.08
    stroy
    -0.08
     pressing
    -0.08
    åĭ¤å¥ĭ
    -0.07
    ãģĵãģ¨ãģĮãģ§ãģį
    -0.07
    osal
    -0.07
    POSITIVE LOGITS
    çĵľ
    0.11
    èĩªç§°
    0.10
    åı¦ä¸ĢåįĬ
    0.10
    æĸ°å¼Ģ
    0.10
    åį³å°Ĩ
    0.09
    æĬīæĭ©
    0.09
    ä»·ä½į
    0.09
    ãģĵãĤĮãģĭãĤī
    0.09
    æĿ¥ä¸´
    0.09
    汶
    0.09
    Activations Density 0.090%

    No Known Activations