© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44149
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
    avana
    -0.07
    νοÏį
    -0.07
    ozy
    -0.07
    unis
    -0.07
    oku
    -0.07
     cÆ°á»Ŀi
    -0.07
    ãĤ¸ãĥ«
    -0.07
    اÙħر
    -0.07
     Frans
    -0.07
    otur
    -0.07
    POSITIVE LOGITS
    ä¹ĥ
    0.07
    ç³»
    0.07
    ery
    0.07
    è°·
    0.06
    stream
    0.06
     Gosp
    0.06
    åı¯ä»¥çĶ±
    0.06
    izi
    0.06
    ä¾į
    0.06
    éĽģ
    0.06
    Activations Density 0.011%

    No Known Activations