© 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. 31417
    Prev
    Next
    INDEX
    Explanations

    commands and files

    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
    anonymous
    -0.10
    æ°ijéĹ´
    -0.08
    ALSE
    -0.08
    ä»ĭ
    -0.08
     Anonymous
    -0.08
    Anonymous
    -0.08
    Pok
    -0.08
    ائر
    -0.08
    cribe
    -0.08
    æĬķæľº
    -0.08
    POSITIVE LOGITS
    éħįå¥Ĺ
    0.21
     accompanying
    0.19
     accompany
    0.17
    éħįå¥Ĺ设æĸ½
    0.16
    åľ¨ä¸ĢæĹģ
    0.15
    éĻĦåĬł
    0.15
     accompanies
    0.15
    çĽ¸ä¼´
    0.14
    ä¼´éļı
    0.13
    ä»ĺãģį
    0.12
    Activations Density 1.015%

    No Known Activations