© 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. 22898
    Prev
    Next
    INDEX
    Explanations

    programming language and efforts

    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
    é¹ĥ
    -0.09
    è´¨åľ°
    -0.09
     UNUSED
    -0.09
    oug
    -0.09
    èħ¥
    -0.09
    综åIJĪæĢ§
    -0.08
    æĭį
    -0.08
     pracy
    -0.08
    åŃIJéĩĮ
    -0.08
    综åIJĪç´łè´¨
    -0.08
    POSITIVE LOGITS
    eyer
    0.10
    åĻ¨
    0.10
    ilton
    0.10
    vara
    0.10
    åijĺ
    0.09
    ETERS
    0.09
    ราย
    0.09
    ending
    0.09
    oras
    0.09
    eated
    0.09
    Activations Density 0.025%

    No Known Activations