© 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. 8065
    Prev
    Next
    INDEX
    Explanations

    learners, language, dictionaries, ESL, ELL

    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
    åı£å¾Ħ
    -0.10
    æĮŀ
    -0.09
    Ñıн
    -0.08
    伪
    -0.08
    åħ¥åºĵ
    -0.08
    zeich
    -0.08
     à¸ĺ
    -0.08
    å±ģèĤ¡
    -0.08
    stad
    -0.08
    quina
    -0.08
    POSITIVE LOGITS
    éĽħæĢĿ
    0.13
    èĭ±è¯Ń
    0.12
    æīĺç¦ı
    0.12
     ESL
    0.11
    åľ°éģĵ
    0.10
     English
    0.10
    çĴ§
    0.10
    elts
    0.10
    åľ¨åħ¨çIJĥ
    0.10
    ELL
    0.09
    Activations Density 0.208%

    No Known Activations