© 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. 11951
    Prev
    Next
    INDEX
    Explanations

    option sellers hedge broker

    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
    纨
    -0.10
    åŃĺéĩı
    -0.10
    éĥİ
    -0.09
    iot
    -0.09
    è¿Ļç§įäºĭæĥħ
    -0.09
    å¢ŀéĩı
    -0.08
    LOPT
    -0.08
    çŃĶåį·
    -0.08
    è¿Ļå°±
    -0.08
    æĹłç©·
    -0.08
    POSITIVE LOGITS
    rote
    0.09
    unar
    0.09
    å¯Įæ°ij
    0.09
     Synd
    0.09
    pcb
    0.08
    é«ĺå±±
    0.08
     Phil
    0.08
    ä»»ä½ķä¸Ģ个
    0.08
    å±±åºĦ
    0.08
    agenta
    0.08
    Activations Density 0.053%

    No Known Activations