© 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. 39606
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ly or ally

    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
    lessly
    -0.12
    è¯Ŀ说
    -0.10
    åĴĮå°ļ
    -0.10
    ened
    -0.10
    ify
    -0.10
    fulness
    -0.10
    /remove
    -0.10
    ãn
    -0.09
    keeper
    -0.09
    åIJĮæł·
    -0.09
    POSITIVE LOGITS
    rics
    0.16
    tics
    0.12
    ev
    0.12
    wed
    0.11
    mph
    0.10
    ¢
    0.10
    è¨ĢãģĪãģ°
    0.10
    -speaking
    0.10
    èŀį为ä¸Ģä½ĵ
    0.10
    rama
    0.09
    Activations Density 0.670%

    No Known Activations