© 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. 49196
    Prev
    Next
    INDEX
    Explanations

    usage instructions

    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
    åģļå¾Ĺ
    -0.10
    ä¸Ģè§Ĵ
    -0.09
    ä¸ĢèĦļ
    -0.08
     Pers
    -0.08
    apis
    -0.08
    èĦļ
    -0.08
    è±ģ
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
    ä¸ĩäºĭ
    -0.08
    kees
    -0.08
    POSITIVE LOGITS
     usage
    0.14
    .usage
    0.12
     Usage
    0.12
    Usage
    0.12
    usage
    0.12
    	usage
    0.11
    _usage
    0.11
     иÑģполÑĮзованиÑı
    0.11
    使ãģĦ
    0.11
    åıªéľĢ
    0.11
    Activations Density 0.180%

    No Known Activations