© 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. 1401
    Prev
    Next
    INDEX
    Explanations

    alternative meaning/action

    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
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    èĢģ人家
    -0.10
    å²Ń
    -0.09
    olla
    -0.09
    okin
    -0.09
    æīĢæıIJä¾Ľä¹ĭ
    -0.08
    omas
    -0.08
    ä¸Ģ身
    -0.08
    ä»ij
    -0.08
    /loading
    -0.08
    POSITIVE LOGITS
    çĬ¬
    0.09
    å½¢æĪIJäºĨ
    0.09
    éĸ
    0.08
    onet
    0.08
    éħ¬
    0.08
    Means
    0.08
    yar
    0.08
    wow
    0.08
    åĽŀæĬ¥
    0.07
    yne
    0.07
    Activations Density 0.005%

    No Known Activations