© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    photographs and images

    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
    omer
    -0.09
    enal
    -0.09
    y
    -0.08
    çĵ®
    -0.08
     NCAA
    -0.08
    омеÑĢ
    -0.08
    å°Ŀ
    -0.07
     Dou
    -0.07
     episode
    -0.07
     CONTR
    -0.07
    POSITIVE LOGITS
    cores
    0.11
    ected
    0.10
    çªĹå¤ĸ
    0.10
    é£ı
    0.09
    çİ°å®ŀä¸Ń
    0.09
    internet
    0.09
    è¿ľæĸ¹
    0.09
    翦
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    plet
    0.09
    Activations Density 0.048%

    No Known Activations