© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    contact us to improve

    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
    èĢģæĿ¿
    -0.10
    дей
    -0.09
    èIJ½åľ°
    -0.09
    åĪĪ
    -0.09
    ullan
    -0.09
    ä¸ĸ代
    -0.09
    é£ŀ
    -0.09
    å°ijæķ°æ°ijæĹı
    -0.08
    åķĨä¸ļåĮĸ
    -0.08
    åı¹æģ¯
    -0.08
    POSITIVE LOGITS
    ypad
    0.09
    dex
    0.08
    heel
    0.08
    èĮ¸
    0.08
    ä¼¼ä¹İæĺ¯
    0.08
    çĻ¾èĬ±
    0.08
    abaj
    0.08
    åģļå¾Ĺ
    0.08
    uber
    0.08
    Exclude
    0.07
    Activations Density 0.010%

    No Known Activations