© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35640
    Prev
    Next
    INDEX
    Explanations

    school and its related entities

    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
    åħħæ²Ľ
    -0.10
    èŀºä¸Ŀ
    -0.09
    æ··
    -0.09
     Gameplay
    -0.09
    èĩªæĿ¥
    -0.09
    GING
    -0.09
    ãĥĨãĥ³
    -0.09
    ging
    -0.08
    itech
    -0.08
    æ´Ħ
    -0.08
    POSITIVE LOGITS
     censor
    0.08
    odon
    0.08
    ä»ĸåıĪ
    0.08
     PropertyInfo
    0.08
    UNT
    0.08
    onaut
    0.08
     district
    0.08
    åĢ«
    0.08
    rov
    0.08
    ä¸įå®ļ
    0.08
    Activations Density 0.039%

    No Known Activations