© 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. 20221
    Prev
    Next
    INDEX
    Explanations

    growth and increase

    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
    æĽ´æ·±
    -0.08
     Rug
    -0.08
    (IService
    -0.08
    æ·±
    -0.08
     Rosenstein
    -0.08
    REAK
    -0.08
    abouts
    -0.08
    æ§İ
    -0.08
    aul
    -0.08
    çĶŁçī©åѦ
    -0.08
    POSITIVE LOGITS
    å¢ŀéķ¿
    0.19
    çļĦå¢ŀéķ¿
    0.18
    å¿«éĢŁå¢ŀéķ¿
    0.15
     growing
    0.15
    è¶ĬæĿ¥è¶Ĭ大
    0.14
     grow
    0.14
     grows
    0.13
    è¿ħçĮĽ
    0.13
    æĹ¥çĽĬ
    0.13
     growth
    0.13
    Activations Density 0.200%

    No Known Activations