© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20298
    Prev
    Next
    INDEX
    Explanations

    concepts and conceptually

    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
    å®ŀçī©
    -0.08
    TC
    -0.08
    ãģ¿ãģª
    -0.08
    åĽ½æĥħ
    -0.07
    OME
    -0.07
     Weekly
    -0.07
     contr
    -0.07
    èĮĥ
    -0.07
    ome
    -0.07
     Physiology
    -0.07
    POSITIVE LOGITS
     concepts
    0.21
    æ¦Ĥ念
    0.19
     Concepts
    0.17
    çļĦæ¦Ĥ念
    0.15
    åİŁçIJĨ
    0.13
     ê°ľëħIJ
    0.13
    cepts
    0.13
    Concept
    0.13
    çŁ¥è¯ĨçĤ¹
    0.12
     concept
    0.12
    Activations Density 0.210%

    No Known Activations