© 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. 26918
    Prev
    Next
    INDEX
    Explanations

    money and accounts

    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
    uchi
    -0.09
    odom
    -0.09
    implicitly
    -0.09
    wich
    -0.08
    stroy
    -0.08
    unger
    -0.08
    Tumblr
    -0.08
    大家åĪĨ享
    -0.08
    çļĦå¿ĥ
    -0.08
    marshall
    -0.07
    POSITIVE LOGITS
    蹶
    0.09
    躬
    0.09
    ä¹Łå¥½
    0.09
    è¢ĭ
    0.09
    æľĢåħ³éĶ®
    0.09
    累累
    0.09
    å±ŀäºİèĩªå·±
    0.09
    åįģéĩĮ
    0.09
    æĺŁçIJĥ
    0.09
     lÆ°ng
    0.09
    Activations Density 0.018%

    No Known Activations