© 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. 38764
    Prev
    Next
    INDEX
    Explanations

    seeing, holding, experiencing life events

    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
    夤
    -0.10
    è¶Ĭæĺ¯
    -0.09
     ph
    -0.09
    èIJ½
    -0.09
    åijĨ
    -0.09
    ä¸ĭæĿ¥çļĦ
    -0.09
    æºľ
    -0.09
    -hook
    -0.09
    ä¸ĭåİ»
    -0.09
    zn
    -0.09
    POSITIVE LOGITS
    亲æīĭ
    0.14
    äº²çľ¼
    0.12
    亲èĩª
    0.11
    享åıĹåĪ°
    0.11
    èĥľåĪ©
    0.10
    çľĭåĪ°
    0.10
    åĵģå°Ŀ
    0.09
    åĴ«
    0.09
    æŁ¥çľĭ详æĥħ
    0.09
    åIJĥåĪ°
    0.09
    Activations Density 0.054%

    No Known Activations