© 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. 35864
    Prev
    Next
    INDEX
    Explanations

    leading, first, early, pioneering

    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
    åѤåĦ¿
    -0.09
     ì§
    -0.09
    çĥ
    -0.09
    å½ĵ代
    -0.09
    anel
    -0.09
     Bever
    -0.09
    elves
    -0.09
    åĬ©æīĭ
    -0.09
    å¼ĺ
    -0.09
    oproject
    -0.08
    POSITIVE LOGITS
    æľĢæĹ©
    0.21
    çİĩåħĪ
    0.20
    æľĢæĹ©çļĦ
    0.17
    æľĢåħĪ
    0.17
    æĬ¢åħĪ
    0.17
    åħĪè¡Į
    0.15
     earliest
    0.14
    èµ°åľ¨
    0.14
     pione
    0.14
    第ä¸Ģæī¹
    0.13
    Activations Density 0.090%

    No Known Activations