© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    data analysis

    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
    itas
    -0.10
    å¼ıçļĦ
    -0.09
    ãĤ¼
    -0.09
    IFORM
    -0.09
    æľŁåĨħ
    -0.09
    ÙĨشر
    -0.09
     há»Ļ
    -0.09
    çŃĩ
    -0.09
    zes
    -0.09
    ismet
    -0.09
    POSITIVE LOGITS
    稽
    0.09
    afi
    0.09
    çļĦ羣å®ŀæĢ§
    0.09
     Commissioner
    0.08
    é³ĥ
    0.08
    éĶī
    0.08
    åľ¬
    0.08
    è¿·ä¿¡
    0.08
     Kut
    0.08
    è§ģéĿ¢
    0.08
    Activations Density 0.125%

    No Known Activations