© 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. 4534
    Prev
    Next
    INDEX
    Explanations

    generating, receiving, or transmitting signals

    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
    éĿ¢åIJij
    -0.09
    表çĻ½
    -0.09
    ä»»ä½ķ人
    -0.08
    ราà¸Ĭà¸ģาร
    -0.08
    çĨı
    -0.08
     ÙĪاÙĦÙģ
    -0.08
     dumpster
    -0.08
    YRO
    -0.08
    çľĭ书
    -0.08
    åįļ主
    -0.08
    POSITIVE LOGITS
     signals
    0.19
    ä¿¡åı·
    0.19
    signals
    0.15
     Signals
    0.15
    æĮĩ令
    0.14
    Signals
    0.14
     signal
    0.14
     Ñģигнал
    0.13
    åĪ°æĿ¥
    0.13
    æĿ¥èĩª
    0.12
    Activations Density 0.333%

    No Known Activations