© 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. 30342
    Prev
    Next
    INDEX
    Explanations

    words starting with i

    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
    orem
    -0.09
     van
    -0.08
    éĺ
    -0.08
    俺
    -0.08
    è¡Į
    -0.08
     brush
    -0.07
    ãĥĮ
    -0.07
    stoff
    -0.07
    um
    -0.07
    Homepage
    -0.07
    POSITIVE LOGITS
    太æŀģ
    0.10
    å¿«æĬ¥
    0.10
    ease
    0.10
    éĻ¤æѤ
    0.09
    è¿Ļä¹Ī大
    0.09
     gái
    0.09
     petty
    0.09
    çİ«
    0.09
    å°ıå°ı
    0.09
    ä¸ĢæĹı
    0.09
    Activations Density 0.105%

    No Known Activations