© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2240
    Prev
    Next
    INDEX
    Explanations

    representation notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Õ»
    -0.07
     classific
    -0.07
    umpf
    -0.07
    çī¹æĸ¯
    -0.06
    çĤ¹å¤ļ
    -0.06
    毡
    -0.06
    ä¸Ģ身
    -0.06
    ÅĤoÅĽci
    -0.06
    çĩĥ
    -0.06
    å°ıå¹³
    -0.06
    POSITIVE LOGITS
     notation
    0.09
     representation
    0.09
     representations
    0.09
     representing
    0.08
    代表
    0.08
    ipa
    0.08
    .zone
    0.08
     REPRESENT
    0.07
     Representation
    0.07
    engu
    0.07
    Activations Density 0.001%

    No Known Activations