© 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. 19145
    Prev
    Next
    INDEX
    Explanations

    math notation and code

    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
    ½
    -0.07
    VILLE
    -0.07
    WISE
    -0.07
    ville
    -0.06
    edList
    -0.06
    toa
    -0.06
    Åij
    -0.06
     ÏĢλÎŃον
    -0.06
    utip
    -0.06
    okka
    -0.06
    POSITIVE LOGITS
    éľį
    0.07
    åħ¨éĥ¨è¯Ħ论
    0.07
    çijŀæĭī
    0.07
    èĩªè¡ĮæıIJä¾Ľ
    0.07
    å±ħåīį
    0.07
    tól
    0.06
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    0.06
    coil
    0.06
    dukung
    0.06
    éĢĨ
    0.06
    Activations Density 0.082%

    No Known Activations