© 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. 8860
    Prev
    Next
    INDEX
    Explanations

    battery life

    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
    ../../../
    -0.10
    æķ´ä½ĵ
    -0.09
    ont
    -0.08
    ned
    -0.08
     overall
    -0.08
    ìĤ¬íķŃ
    -0.08
     stature
    -0.08
    ion
    -0.08
    ual
    -0.08
    å¼Ħ
    -0.08
    POSITIVE LOGITS
    .tc
    0.10
    гоÑĢ
    0.09
     Cuomo
    0.09
    æĪijåıªæĺ¯
    0.09
    inia
    0.09
    æĹı
    0.08
    ä¾ł
    0.08
    -backed
    0.08
    çĽĪ
    0.08
     Holt
    0.08
    Activations Density 0.031%

    No Known Activations