© 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. 61670
    Prev
    Next
    INDEX
    Explanations

    Digital Privacy, government speech, federal cases

    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
    leaning
    -0.09
    ABCDEFGHIJKLMNOP
    -0.09
    å°ıç¼ĸ
    -0.08
    示æĦı
    -0.08
    æħij
    -0.08
    lexport
    -0.08
    _AGENT
    -0.08
    æĴŃ
    -0.08
    å¾Īå¤ļæľĭåıĭ
    -0.08
    èĨº
    -0.08
    POSITIVE LOGITS
    æľīæķĪæĢ§
    0.11
    éĻ¤éĿŀ
    0.10
    åĴĮå°ļ
    0.10
     Retro
    0.10
    çıº
    0.10
    çŃīä¸Ģæī¹
    0.09
    çħ
    0.09
     обÑıзан
    0.09
    åīĸ
    0.09
     retro
    0.09
    Activations Density 0.393%

    No Known Activations