© 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. 27601
    Prev
    Next
    INDEX
    Explanations

    contained in or on

    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
    omat
    -0.10
    æĸĩåĮĸçļĦ
    -0.09
    åľ°æ®µ
    -0.09
    PropertyParams
    -0.09
    èĭ±æł¼
    -0.09
    (CultureInfo
    -0.09
    æĸĩåĮĸ建设
    -0.09
    çIJ¼
    -0.09
    HeaderCode
    -0.08
    ppe
    -0.08
    POSITIVE LOGITS
    antly
    0.10
    åįij
    0.09
    æĻ®
    0.09
    åı£å¾Ħ
    0.08
    elix
    0.08
     uÄŁ
    0.08
     Robbins
    0.08
     Helm
    0.08
    itta
    0.08
    leys
    0.08
    Activations Density 0.012%

    No Known Activations