© 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. 20339
    Prev
    Next
    INDEX
    Explanations

    Royal and historical names

    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
    æľįä»İ
    -0.10
    izza
    -0.09
    çŃĿ
    -0.09
    åįķä»·
    -0.09
    çłĶ究æīĢ
    -0.09
    æļ´
    -0.09
    èµ·éĩį
    -0.09
    åħ³éŨ
    -0.09
    è¡Įéķ¿
    -0.09
    åĴ½
    -0.09
    POSITIVE LOGITS
     analy
    0.08
    رش
    0.08
    å½ĵä½ł
    0.08
     нед
    0.08
     Syndrome
    0.07
    пал
    0.07
    åħ¨åĬĽæīĵéĢł
    0.07
    å¿ĥæĦı
    0.07
    TD
    0.07
    èħº
    0.07
    Activations Density 0.011%

    No Known Activations