© 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. 33268
    Prev
    Next
    INDEX
    Explanations

    buying dollar, winning schools, accepted value

    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
    resents
    -0.07
    åĽŀå¸ĸ
    -0.07
    æĿ¥äºº
    -0.07
    (attrs
    -0.07
    éĶ¤
    -0.06
    å«£
    -0.06
    enz
    -0.06
    IES
    -0.06
     Bust
    -0.06
    ATAN
    -0.06
    POSITIVE LOGITS
    ksam
    0.08
    _EOF
    0.08
     consists
    0.08
    éģĤ
    0.07
     Maret
    0.07
     consist
    0.07
    容
    0.07
    év
    0.07
    ulut
    0.07
    ron
    0.07
    Activations Density 0.025%

    No Known Activations