© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 3209
    Prev
    Next
    INDEX
    Explanations

    gain / gained

    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¬èº«å°±æĺ¯
    -0.09
    lasses
    -0.09
    就没æľī
    -0.08
    天èĬ±æĿ¿
    -0.08
    æĭ¿åĩºæĿ¥
    -0.08
    ÑģоÑģ
    -0.08
    .logical
    -0.08
    çĥ
    -0.08
    lass
    -0.08
    Throwable
    -0.08
    POSITIVE LOGITS
    æ°ijå¿ĥ
    0.14
    æĪ¾
    0.10
    å®ŀè·µç»ıéªĮ
    0.10
    åľ¨çĶŁæ´»ä¸Ń
    0.09
    èIJĮ
    0.09
    гад
    0.09
    åĪ©åύ
    0.09
    shade
    0.09
    æŁ¥çľĭåħ¨æĸĩ
    0.09
    大åıij
    0.08
    Activations Density 0.044%

    No Known Activations