© 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. 6922
    Prev
    Next
    INDEX
    Explanations

    equinoxes and summers

    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
    orts
    -0.08
    é¹³
    -0.08
    ä¹ĸ
    -0.08
    otope
    -0.08
    é«Ń
    -0.08
    å¢Ł
    -0.08
    nee
    -0.08
    è¡¿
    -0.08
    ãĤ¾
    -0.08
    ifo
    -0.08
    POSITIVE LOGITS
    deps
    0.10
    大家ä¸Ģèµ·
    0.09
    åIJ¼
    0.09
    imar
    0.09
    æĥħ人
    0.09
    è¾Ļ
    0.09
    inqu
    0.09
    çªŁ
    0.09
     Lust
    0.09
    æĻı
    0.08
    Activations Density 0.004%

    No Known Activations