© 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. 5911
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    èĬĻ
    -0.11
    eda
    -0.10
    缸符
    -0.09
    åįĬå¤ľ
    -0.08
    ç»Ī身
    -0.08
    鹧
    -0.08
    åĪ°è¿ĻéĩĮ
    -0.08
     водÑĭ
    -0.08
    åľ¨è¿ĻéĩĮ
    -0.08
    鸳
    -0.08
    POSITIVE LOGITS
     portion
    0.13
     ÑĩаÑģÑĤÑĮ
    0.12
     czÄĻÅĽÄĩ
    0.11
     portions
    0.11
    éĥ¨åĪĨ
    0.11
    hort
    0.10
    iores
    0.10
     kısmı
    0.10
     part
    0.10
    portion
    0.10
    Activations Density 0.094%

    No Known Activations