© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51432
    Prev
    Next
    INDEX
    Explanations

    expectations of what

    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
    -zone
    -0.09
    åľ¨æŃ¤ä¹ĭåīį
    -0.09
    zones
    -0.09
    åľ¨ç½ijä¸Ĭ
    -0.09
    åĮĹè·¯
    -0.08
    èĮģ
    -0.08
    (zone
    -0.08
    _prices
    -0.08
    éľĢè¦ģç͍
    -0.08
    åĪĨå¸ĥåľ¨
    -0.08
    POSITIVE LOGITS
    æ²¥
    0.10
    åħ·æľīèī¯å¥½
    0.10
    _HS
    0.09
    æ¯ıä¸Ģ个人
    0.09
    åħ»æĪIJ
    0.09
    ç¹ĩ
    0.09
    æĿł
    0.09
    него
    0.08
    æ·³
    0.08
     qualities
    0.08
    Activations Density 0.091%

    No Known Activations