© 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. 41166
    Prev
    Next
    INDEX
    Explanations

    electrode, anode, cathode

    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
    份
    -0.08
    ä¸İæľ¬ç«Ļ
    -0.07
    aternity
    -0.07
    beer
    -0.07
    åŃĺéĩı
    -0.07
    çĶ¨çľ¼
    -0.07
    åŃĺåĤ¨åľ¨
    -0.07
     mut
    -0.07
    _PARAMETER
    -0.07
    大路
    -0.07
    POSITIVE LOGITS
     electrodes
    0.09
    çĶµæŀģ
    0.09
    หà¸Ļà¹īาà¸Ĺีà¹Ī
    0.08
    éĻĦè¿ijçļĦ
    0.08
     electrode
    0.08
    å¤ĦçļĦ
    0.08
     оÑģнаÑīен
    0.07
    ä¸Ĭæľī
    0.07
     waarop
    0.07
    ponge
    0.07
    Activations Density 0.014%

    No Known Activations