© 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. 39437
    Prev
    Next
    INDEX
    Explanations

    German places, organizations, and technical terms

    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
    ä¸ĢåĪĢ
    -0.08
    ä¸ĢåĪĨéĴ±
    -0.08
    æĬ½æŁ¥
    -0.08
    alette
    -0.08
    łí
    -0.08
    ÑĢог
    -0.08
    à¹Ģà¸Ńา
    -0.08
    berman
    -0.08
    lobals
    -0.08
    ÄĻż
    -0.08
    POSITIVE LOGITS
    æĺ¯æľĢ
    0.09
    æľ¬ç½ij
    0.09
    å¤ĸåĽ½äºº
    0.09
    è¿ĺä¸įæĺ¯
    0.09
    astics
    0.09
    åĽ¾çĶ»
    0.08
    åĪį
    0.08
    learn
    0.08
    å¾Īé«ĺçļĦ
    0.08
    llib
    0.08
    Activations Density 0.376%

    No Known Activations