© 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. 18414
    Prev
    Next
    INDEX
    Explanations

    back 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
    ä¸ĢéĿ¢
    -0.10
    baru
    -0.09
    бил
    -0.09
    acia
    -0.09
    mere
    -0.09
    æħ¢
    -0.08
    æľĢç»Ī
    -0.08
    ä½ķç§į
    -0.08
    nist
    -0.08
    åıįèĢĮ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    åĽŀåĪ°
    0.09
    eland
    0.08
    idel
    0.08
    åĽŀåĪ°äºĨ
    0.08
    å§ŀ
    0.08
     Affero
    0.08
    çĪĨåĩº
    0.08
    ç½ij讯
    0.08
    足迹
    0.08
    Activations Density 0.020%

    No Known Activations