© 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. 61105
    Prev
    Next
    INDEX
    Explanations

    ancient history / geology

    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
    èIJ½
    -0.12
    é£ŀ
    -0.10
    æıŃéľ²
    -0.09
    麾
    -0.09
    ench
    -0.09
    é£Ľ
    -0.08
    æĸ°éĻĪ代谢
    -0.08
    æ´»è·ĥ
    -0.08
    ТЬ
    -0.08
    åݨæĪ¿
    -0.08
    POSITIVE LOGITS
    èŀ«
    0.10
    opro
    0.09
     вн
    0.09
    rud
    0.09
    Anc
    0.09
    captures
    0.08
    implements
    0.08
     sublist
    0.08
     kut
    0.08
     Ancient
    0.08
    Activations Density 0.095%

    No Known Activations