© 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. 36686
    Prev
    Next
    INDEX
    Explanations

    article followed by topic/source

    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
    ingly
    -0.11
    est
    -0.10
    inct
    -0.10
    cape
    -0.09
    .utc
    -0.09
    brook
    -0.09
    ITAL
    -0.09
    å¾Ĺä½ı
    -0.09
    çi
    -0.08
    å±Ī
    -0.08
    POSITIVE LOGITS
    owell
    0.09
    /wiki
    0.09
    ãĥ³
    0.08
    çİ
    0.08
    åł±å°İ
    0.08
    หา
    0.08
    èĦijæµ·
    0.08
    aceous
    0.08
    -worthy
    0.08
    /video
    0.08
    Activations Density 0.026%

    No Known Activations