© 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. 2803
    Prev
    Next
    INDEX
    Explanations

    of the / de la / in your name

    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
    net
    -0.10
    è¡Ĺä¸Ĭ
    -0.10
    _MACRO
    -0.10
    åģıåģı
    -0.09
    æĮĩçļĦæĺ¯
    -0.09
    NET
    -0.09
    InitialState
    -0.09
    æīĭèĦļ
    -0.09
    ä¿Ł
    -0.08
    æĪĸå¤ļ
    -0.08
    POSITIVE LOGITS
    çļĦåĪ©çĽĬ
    0.09
    ä»ĵ
    0.09
    åĪ©çĽĬ
    0.09
     interests
    0.08
    è¡Įäºĭ
    0.08
    让æĤ¨
    0.08
    峡
    0.08
    asso
    0.08
    ä½łèĩªå·±
    0.08
    undy
    0.08
    Activations Density 0.068%

    No Known Activations