© 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. 22772
    Prev
    Next
    INDEX
    Explanations

    settings or preferences

    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
    æľªç»ıæİĪæĿĥ
    -0.09
    VOKE
    -0.09
    对æĪijæĿ¥è¯´
    -0.09
    为ä¹ĭ
    -0.08
    qu
    -0.08
    FA
    -0.08
    é¦ĸ款
    -0.08
     FA
    -0.08
    å²Ĺ
    -0.08
    ingu
    -0.08
    POSITIVE LOGITS
     settings
    0.13
    (Settings
    0.12
     Settings
    0.12
    设置
    0.11
    Settings
    0.11
    settings
    0.11
     SETTINGS
    0.11
     options
    0.11
     Preferences
    0.10
    SETTINGS
    0.10
    Activations Density 0.161%

    No Known Activations