© 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. 60549
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or words

    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
    æĮĿ
    -0.10
    swick
    -0.09
    shaw
    -0.07
    æĮ¥éľį
    -0.07
    èĤ¿
    -0.07
    kamp
    -0.07
    emark
    -0.07
    æľ½
    -0.07
    zor
    -0.07
    ÙħاÙĨ
    -0.07
    POSITIVE LOGITS
    ettet
    0.07
    å¼Ģæĭį
    0.06
     behalf
    0.06
    ett
    0.06
    éĤĢæĤ¨
    0.06
    ROTO
    0.06
     vers
    0.06
    oud
    0.06
    å½ĴæĿ¥
    0.06
    bet
    0.06
    Activations Density 0.082%

    No Known Activations