© 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. 51001
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and human evolution

    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
    æĬ¥ç¤¾
    -0.09
    åħĪè¿Ľåįķä½į
    -0.09
    ç¥ŀåľ£
    -0.09
    ãĤ¯ãĥĪ
    -0.08
    è¿ĻåĿĹ
    -0.08
     маÑĤеÑĢи
    -0.08
    åij¨åĪĬ
    -0.08
    bir
    -0.08
    _OT
    -0.08
    满足
    -0.08
    POSITIVE LOGITS
    稳妥
    0.11
    -human
    0.10
    妥
    0.10
     human
    0.09
    _human
    0.09
    åĬłå¿«åıijå±ķ
    0.09
    伦çIJĨ
    0.09
    忧èĻij
    0.09
    é©Ń
    0.09
     pose
    0.09
    Activations Density 0.067%

    No Known Activations