© 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. 35022
    Prev
    Next
    INDEX
    Explanations

    battery pack capacity

    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
    ä¸ĩåı°
    -0.10
    沸
    -0.09
    æĬ¼ãģĹ
    -0.09
    ordinal
    -0.09
    åĢĴ
    -0.09
    åģı
    -0.08
    éĻ·
    -0.08
     ordinal
    -0.08
    è®®
    -0.08
    uib
    -0.08
    POSITIVE LOGITS
    èĤ®
    0.10
    çĬģ
    0.09
     Amar
    0.09
    寿åij½
    0.09
    åĩºèµĦ
    0.09
    饱满
    0.09
     Batter
    0.09
    åĹĶ
    0.09
    åĽ½ç±į
    0.09
     кÑĢÑĭ
    0.09
    Activations Density 0.060%

    No Known Activations