© 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. 33161
    Prev
    Next
    INDEX
    Explanations

    long wait or anticipation

    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
    æĶ¯æĮģåĬĽåº¦
    -0.09
    enberg
    -0.09
    åģļå¾Ĺ
    -0.09
    ehler
    -0.08
    åĵªéĩĮ
    -0.08
    fty
    -0.08
    åĸĦæĦı
    -0.08
    enna
    -0.08
    heck
    -0.08
    èĮĦåŃIJ
    -0.08
    POSITIVE LOGITS
    çĽ¼æľĽ
    0.17
    å·²ä¹ħçļĦ
    0.16
    æľŁçĽ¼
    0.16
    çĽ¼
    0.14
    ollen
    0.13
    ç»Īäºİ
    0.12
    èĭ¦èĭ¦
    0.12
    渴
    0.11
    æĢ¥
    0.11
    å·²ä¹ħ
    0.11
    Activations Density 0.057%

    No Known Activations