© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21902
    Prev
    Next
    INDEX
    Explanations

    many of the

    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
    cott
    -0.10
    çī¹å®ļ
    -0.10
    enk
    -0.10
    ä¸ĢåIJį
    -0.09
    (Call
    -0.09
     footage
    -0.09
     evidence
    -0.08
    æľīæŶåĢĻ
    -0.08
    åīįæıIJ
    -0.08
    éĿŀ常
    -0.08
    POSITIVE LOGITS
    å©¿
    0.11
    ToMany
    0.10
    åĮ¹
    0.10
    èĬ±èįī
    0.09
    æĪij们ä¼ļ
    0.09
    æİĮæı¡äºĨ
    0.09
    éħį件
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    phas
    0.09
    ëĵ¤
    0.09
    Activations Density 0.020%

    No Known Activations