© 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. 34721
    Prev
    Next
    INDEX
    Explanations

    electron properties and interactions

    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
    ä¹ĭä¸Ģ
    -0.10
     prefixes
    -0.09
    دÙĬ
    -0.08
    人æ°ij
    -0.08
    ×ľ×ª
    -0.08
    vor
    -0.08
    ä¸įåIJĪçIJĨ
    -0.08
    isle
    -0.08
    NESS
    -0.08
    ILI
    -0.08
    POSITIVE LOGITS
    erk
    0.10
    esco
    0.10
    å¹ķ
    0.10
    æ·«
    0.10
    thern
    0.09
    innen
    0.09
    æĢ»æķ°
    0.09
    icients
    0.09
    еÑĩно
    0.09
    æ¶Īè´¹åĵģ
    0.09
    Activations Density 0.105%

    No Known Activations