© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19924
    Prev
    Next
    INDEX
    Explanations

    boiling point and volatile compounds

    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
    åĨ²
    -0.09
    æķ¦
    -0.09
    丼
    -0.08
    è¿ĩæĿ¥
    -0.08
    uto
    -0.08
     nic
    -0.08
    uted
    -0.08
    oni
    -0.08
    cone
    -0.07
    主管éĥ¨éŨ
    -0.07
    POSITIVE LOGITS
    é¦ı
    0.12
    沸
    0.11
    åįĩåįİ
    0.11
     Fulton
    0.11
    åħ¸
    0.10
     Vapor
    0.10
    æĮ¥åıij
    0.10
     vapor
    0.10
    èĴ¸æ±½
    0.10
    anje
    0.10
    Activations Density 0.098%

    No Known Activations