© 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. 22621
    Prev
    Next
    INDEX
    Explanations

    foam rolling, Field of the Invention

    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
    踱
    -0.09
    çĽijçĭ±
    -0.08
     TRADE
    -0.08
    ç³ĸå°¿çĹħ
    -0.08
    elyn
    -0.08
    æŃĮèĪŀ
    -0.08
    .mount
    -0.08
    æ¤ħ
    -0.08
    æĺĻ
    -0.08
     gar
    -0.08
    POSITIVE LOGITS
    åĮį
    0.14
    趴
    0.14
    è¶´åľ¨
    0.12
    çĪ¬
    0.12
    衾
    0.11
    åį§
    0.11
    èººåľ¨
    0.11
    躺çĿĢ
    0.11
     crawl
    0.10
    翻身
    0.10
    Activations Density 0.036%

    No Known Activations