© 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. 18387
    Prev
    Next
    INDEX
    Explanations

    then i

    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
    å±ĬæŶ
    -0.10
    æѤåIJİ
    -0.10
    æѤæŶ
    -0.09
    éļıåIJİ
    -0.09
     now
    -0.09
    ä»İæѤ
    -0.09
    æĪijçİ°åľ¨
    -0.08
    åŬ
    -0.08
    ç¨Ĺ
    -0.08
     Te
    -0.08
    POSITIVE LOGITS
    å°±éľĢè¦ģ
    0.10
    麻çĥ¦
    0.09
    å°±ä¸į
    0.09
    ç®į
    0.09
    aar
    0.09
    ç¬ijè¯Ŀ
    0.09
    å¾Ĺ太
    0.09
    èĢĥéªĮ
    0.09
    侯
    0.08
    第ä¸ī次
    0.08
    Activations Density 0.069%

    No Known Activations