© 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. 55584
    Prev
    Next
    INDEX
    Explanations

    D-dimensional

    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
     dobr
    -0.09
     Highlands
    -0.09
    ctl
    -0.09
    licos
    -0.09
    å¤ĸç§ij
    -0.09
    æĪ¢
    -0.09
    ocale
    -0.09
    æݥ纳
    -0.08
    inel
    -0.08
    sız
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.13
    æµħ
    0.09
    ç»IJ
    0.09
    imensional
    0.09
    èĸª
    0.09
     Sac
    0.09
    篾
    0.09
     одно
    0.08
    鲤
    0.08
    æ¸Ĭ
    0.08
    Activations Density 0.107%

    No Known Activations