© 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. 34667
    Prev
    Next
    INDEX
    Explanations

    inter-related, connected, interdependent

    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
    forg
    -0.09
     khấu
    -0.09
     latter
    -0.09
    .mods
    -0.09
    éĤ£éĩĮ
    -0.09
    emade
    -0.09
    uffix
    -0.09
    ologue
    -0.09
    éĵŃè®°
    -0.08
    ctors
    -0.08
    POSITIVE LOGITS
    æ·Į
    0.10
    ities
    0.10
    å·¥ä½ľçļĦ
    0.10
    çłĶ究表æĺİ
    0.09
    æĢĿç´¢
    0.09
    ç¥Ŀç¦ı
    0.09
    æIJľæķij
    0.08
    ä¸Ģéĺµ
    0.08
    å±ħ室
    0.08
     каж
    0.08
    Activations Density 0.017%

    No Known Activations