© 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. 34080
    Prev
    Next
    INDEX
    Explanations

    email and contact information

    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
    åIJįåĪĹåīįèĮħ
    -0.09
    æµ®
    -0.08
    lero
    -0.08
    为é¦ĸ
    -0.08
    hatt
    -0.08
     blinds
    -0.08
     اÙĦأخ
    -0.08
    åĪĨæł¡
    -0.08
    okin
    -0.08
    è§Ĩéĩİ
    -0.08
    POSITIVE LOGITS
    èģĶç³»æĸ¹å¼ı
    0.20
    æīĭæľºåı·
    0.17
    åIJįçīĩ
    0.15
    åı·çłģ
    0.15
    ä½ıåĿĢ
    0.14
    èģĶç³»çĶµè¯Ŀ
    0.14
    åľ°åĿĢ
    0.13
     contact
    0.13
    çķĻä¸ĭäºĨ
    0.13
    带走
    0.12
    Activations Density 0.070%

    No Known Activations