© 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. 39355
    Prev
    Next
    INDEX
    Explanations

    increasing demand

    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
    åijĺ
    -0.09
    æ¶Ĥ
    -0.08
    omit
    -0.08
    æĢ§åij½
    -0.08
    ÑģеÑĤ
    -0.08
    éĿ¢åŃĶ
    -0.08
    è±¢
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
     Raise
    -0.08
    licht
    -0.08
    POSITIVE LOGITS
     demand
    0.28
    éľĢæ±Ĥ
    0.28
    å¸ĤåľºéľĢæ±Ĥ
    0.26
    çļĦéľĢæ±Ĥ
    0.25
     Demand
    0.24
    demand
    0.23
    Demand
    0.23
    _demand
    0.20
    -demand
    0.19
     demands
    0.19
    Activations Density 0.122%

    No Known Activations