© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 28026
    Prev
    Next
    INDEX
    Explanations

    is the

    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
    æ½ľ
    -0.09
    ä¹ĭä¸Ģ
    -0.08
    æĦļ
    -0.08
    åijĪ
    -0.08
     impl
    -0.08
    ä½ľ
    -0.08
    band
    -0.08
    çĹ°
    -0.08
     Apr
    -0.07
    ips
    -0.07
    POSITIVE LOGITS
    åĪ©çī©
    0.10
    å¿«æĬ¥
    0.09
    зов
    0.09
    åIJĥ饱
    0.09
    åѤåĦ¿
    0.09
    нии
    0.09
    PropertyParams
    0.09
    让åŃ©åŃIJ
    0.09
    vil
    0.09
    ä¸įåłª
    0.09
    Activations Density 0.352%

    No Known Activations