© 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. 53835
    Prev
    Next
    INDEX
    Explanations

    caught up in

    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
    åħ¥ãĤĬ
    -0.10
    .engine
    -0.09
    иков
    -0.09
    é³ŀ
    -0.09
    èĪĴ
    -0.09
    æľīåħ³è§Ħå®ļ
    -0.09
     бил
    -0.09
    exus
    -0.08
     Pou
    -0.08
    ews
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.10
    zer
    0.09
     interrog
    0.09
    rum
    0.09
     Quint
    0.08
     vard
    0.08
    以人æ°ij
    0.08
     tiên
    0.08
    æĹ¥å¸¸
    0.08
    nit
    0.08
    Activations Density 0.007%

    No Known Activations