© 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. 8375
    Prev
    Next
    INDEX
    Explanations

    characteristics of

    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
    åł
    -0.11
    ìį¨
    -0.10
    ight
    -0.10
    hack
    -0.09
    elling
    -0.09
    innacle
    -0.09
    榻
    -0.09
    åįĥåı¤
    -0.09
    æĦŁ
    -0.09
    èĸ®
    -0.09
    POSITIVE LOGITS
    sWith
    0.12
    é²ľæĺİ
    0.11
    ories
    0.11
    nel
    0.11
    ities
    0.09
    iveness
    0.09
    NameValuePair
    0.09
    ties
    0.08
    erner
    0.08
     мом
    0.08
    Activations Density 0.045%

    No Known Activations