© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    examples like

    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
    åĩī
    -0.09
    çĤ·
    -0.09
    _exact
    -0.09
    寡
    -0.09
    äºĨä¸įå°ij
    -0.08
    们éĥ½
    -0.08
    èij³
    -0.08
    涼
    -0.08
    æ·ĸ
    -0.08
    èĭ¥å¹²
    -0.08
    POSITIVE LOGITS
    лаг
    0.09
    表éĿ¢ä¸Ĭ
    0.08
    æĺİæĺİ
    0.08
    abb
    0.08
    ith
    0.08
    pecific
    0.08
    _plain
    0.08
    iance
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    ither
    0.07
    Activations Density 0.058%

    No Known Activations