© 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. 9705
    Prev
    Next
    INDEX
    Explanations

    Rama, Indra, Patil, Akali

    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¸ŃéĢĶ
    -0.10
    对ä¸įèµ·
    -0.09
    åIJIJ
    -0.09
    æĿĤ
    -0.08
    å°ıå°ı
    -0.08
    uw
    -0.08
    åIJįä¹ī
    -0.08
    vision
    -0.08
    åĬ³åĬ¨åĬĽ
    -0.08
    ank
    -0.08
    POSITIVE LOGITS
    åĸ»
    0.10
    èĢģå¦Ī
    0.09
    ermen
    0.09
    ä¹ĹãĤĬ
    0.09
    常çĶ¨
    0.08
    æ²ī浸
    0.08
     çıkar
    0.08
    åĬŀåħ¬
    0.08
    ç¼
    0.08
    fy
    0.08
    Activations Density 0.015%

    No Known Activations