© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20487
    Prev
    Next
    INDEX
    Explanations

    energy efficiency

    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
    Ñĩи
    -0.10
    çIJ¬
    -0.10
    à¹Ģà¸Ńà¸ĩ
    -0.10
    oning
    -0.10
    ä¸įéĶĻçļĦ
    -0.09
    æľįåĬ¡èĥ½åĬĽ
    -0.09
    -unstyled
    -0.09
    WithValue
    -0.09
    ä¸įæ¸ħ
    -0.09
    éģķãģĦ
    -0.09
    POSITIVE LOGITS
     closely
    0.09
    owler
    0.08
    ancing
    0.08
    æķ£
    0.08
    çļĦ对象
    0.08
    nad
    0.07
    arme
    0.07
    olk
    0.07
    amon
    0.07
     Phon
    0.07
    Activations Density 0.021%

    No Known Activations