© 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. 34134
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or letters

    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
    èĢ³
    -0.06
    ickle
    -0.06
    éŀŃ
    -0.06
    ports
    -0.06
    éªļ
    -0.06
     Tone
    -0.06
    çĪ±
    -0.06
    çĦ°
    -0.06
     POST
    -0.06
    ehren
    -0.06
    POSITIVE LOGITS
    anded
    0.08
    æ®Ĭ
    0.08
    éķ¿èħ¿
    0.07
    æĸ°éĥ½
    0.07
    alth
    0.07
    iland
    0.07
    elib
    0.07
    eci
    0.07
    acia
    0.07
    åħ¶äºĮ
    0.07
    Activations Density 0.034%

    No Known Activations