© 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. 57328
    Prev
    Next
    INDEX
    Explanations

    dielectric constant, low resistivity, consume power

    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
    imens
    -0.10
    OpenHelper
    -0.10
    nim
    -0.09
    enal
    -0.09
     |_|
    -0.09
    çļĦäºĭæĥħ
    -0.08
    edImage
    -0.08
    rif
    -0.08
     administrations
    -0.08
    çİ©
    -0.08
    POSITIVE LOGITS
    æĪIJè¯Ń
    0.09
    顶å±Ĥ设计
    0.09
    ä»İä¸ļ
    0.08
    èĶ¬
    0.08
    èij£äºĭéķ¿
    0.08
    èµŃ
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
    è¿ľæĸ¹
    0.08
    æŀµ
    0.08
    ç«ĭæ¡Ī
    0.08
    Activations Density 0.247%

    No Known Activations