© 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. 46976
    Prev
    Next
    INDEX
    Explanations

    increase or decrease

    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
    ekk
    -0.08
    _kw
    -0.07
    ks
    -0.07
    æĮĩå®ļ
    -0.07
    次
    -0.06
     rumpe
    -0.06
    å¼łå»º
    -0.06
    OLI
    -0.06
    mq
    -0.06
    iers
    -0.06
    POSITIVE LOGITS
    è´Ł
    0.11
    negative
    0.10
    è²ł
    0.10
     negative
    0.09
    -negative
    0.09
     reversal
    0.09
    è´ŁçļĦ
    0.09
    æĬµæ¶Ī
    0.09
     Negative
    0.08
    åıį转
    0.08
    Activations Density 0.112%

    No Known Activations