© 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. 56863
    Prev
    Next
    INDEX
    Explanations

    business and related contexts

    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
    éĿ¡
    -0.10
    mark
    -0.09
    å¼Ń
    -0.09
    åħ¬çĽĬæĢ§
    -0.08
    RLF
    -0.08
    vars
    -0.08
    unar
    -0.08
     XK
    -0.08
    ami
    -0.08
    EI
    -0.08
    POSITIVE LOGITS
    åĬŀåħ¬
    0.12
    æĹħéĢĶ
    0.12
    çĶ¨æĪ·æıIJä¾Ľ
    0.10
    æĹħè¡Į
    0.10
    åĩºå·®
    0.10
    åĢŃ
    0.10
    è¸ıä¸Ĭ
    0.09
    å»ĭ
    0.09
     office
    0.09
    å¿ĺ
    0.09
    Activations Density 0.010%

    No Known Activations