© 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. 52369
    Prev
    Next
    INDEX
    Explanations

    robots and robotics

    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
    ogi
    -0.09
    DefaultValue
    -0.08
    _Util
    -0.08
    éĶļ
    -0.08
    è¦ģä¹Ī
    -0.08
    urat
    -0.08
    пÑĥÑĤ
    -0.08
    åijĬè¯īä½ł
    -0.08
    ç¾İçĻ½
    -0.08
    çª
    -0.08
    POSITIVE LOGITS
    æľºåĻ¨äºº
    0.12
    robot
    0.11
     robot
    0.10
    å·¡èĪª
    0.10
    éļľ
    0.10
     robots
    0.09
    Robot
    0.09
    çıŀ
    0.09
    æľªçŁ¥
    0.09
     Robotics
    0.09
    Activations Density 0.171%

    No Known Activations