© 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. 34705
    Prev
    Next
    INDEX
    Explanations

    predominately / -wise / ically

    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
    lots
    -0.09
    ç«ĭéĿ¢
    -0.08
     Listings
    -0.08
     Jedi
    -0.08
    ä¸Ī
    -0.08
    ONSE
    -0.08
    份
    -0.08
     luôn
    -0.08
    ylene
    -0.08
    建çŃijçī©
    -0.08
    POSITIVE LOGITS
    atically
    0.13
    icamente
    0.12
    илÑĮно
    0.10
    éĢļè¿ĩ对
    0.10
    istically
    0.10
     обÑĢазом
    0.10
    ingly
    0.09
    ically
    0.09
    -wise
    0.09
    æ£
    0.09
    Activations Density 0.507%

    No Known Activations