© 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. 18941
    Prev
    Next
    INDEX
    Explanations

    compass directions

    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
    ä½łèĩªå·±
    -0.08
    çĿļ
    -0.08
     Télé
    -0.08
    .fac
    -0.08
    åīįèĢħ
    -0.08
    icy
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    isci
    -0.07
    \_
    -0.07
    çļĦ设计
    -0.07
    POSITIVE LOGITS
    ëįķ
    0.12
    çĽijå¯Ł
    0.11
    å¤ĩ
    0.11
    åľ¨æ¸¸æĪıä¸Ń
    0.10
    anse
    0.10
    ä¸įè´Ł
    0.09
    è¡ĮåĬ¨
    0.09
     defaultMessage
    0.09
    é«ĺåħ´
    0.08
    æĿĨèıĮ
    0.08
    Activations Density 0.035%

    No Known Activations