© 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. 35149
    Prev
    Next
    INDEX
    Explanations

    staring or glaring at

    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
    ilar
    -0.10
    utta
    -0.10
    æħ¢æħ¢åľ°
    -0.09
    rong
    -0.08
     covert
    -0.08
    leine
    -0.08
    arian
    -0.08
    spd
    -0.08
    ÙĬات
    -0.08
    ierung
    -0.08
    POSITIVE LOGITS
    çĽ¯çĿĢ
    0.12
    çļĦ缮åħī
    0.12
    -eyed
    0.12
    еÑĤÑĮ
    0.11
    çľĪ
    0.11
    ä¸Ģçľ¼
    0.11
    æľĽçĿĢ
    0.11
    æĸ°éĹ»ç½ij
    0.10
    çĿ¨
    0.10
    å·²ä¹ħ
    0.10
    Activations Density 0.012%

    No Known Activations