© 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. 30270
    Prev
    Next
    INDEX
    Explanations

    growth

    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
     electrom
    -0.09
    çŃIJ
    -0.08
    çĤĶ
    -0.08
    åIJį家
    -0.08
    åĴ«
    -0.08
    è¯Ģ
    -0.08
    íĨ
    -0.08
     диÑĢ
    -0.08
    说ä¸įåĩº
    -0.08
    缶
    -0.08
    POSITIVE LOGITS
    çĶŁéķ¿
    0.12
    _growth
    0.11
    éĩįçĶŁ
    0.11
     growth
    0.10
    èĮĤ
    0.10
    涨
    0.10
     поб
    0.09
    growth
    0.09
    åĩºæĿ¥çļĦ
    0.09
    åľ¨ç½ij绾
    0.09
    Activations Density 0.064%

    No Known Activations