© 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. 51172
    Prev
    Next
    INDEX
    Explanations

    Fern Ridge, Indian community

    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
    åIJĪæĪIJ
    -0.11
    asar
    -0.10
    عÙĬ
    -0.10
    indr
    -0.10
    æĻ®
    -0.10
    ORN
    -0.09
    åĪĨå·¥
    -0.09
    çģ«çĦ°
    -0.09
    cycles
    -0.09
    èľ
    -0.09
    POSITIVE LOGITS
    æ°´åºĵ
    0.14
    æ°´åĪ©
    0.14
    æ³Ħ
    0.14
    ä¸ĭ游
    0.13
    åł¤
    0.12
    éĺ²æ±Ľ
    0.12
    åĿĿ
    0.12
     dam
    0.12
    ä¸Ĭ游
    0.12
    è¿IJèIJ¥
    0.11
    Activations Density 0.045%

    No Known Activations