© 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. 42137
    Prev
    Next
    INDEX
    Explanations

    probability of sequence picking

    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
    +c
    -0.07
    å¤ĸäºĭ
    -0.07
    az
    -0.07
    -0.07
    深度
    -0.07
    urop
    -0.07
    аз
    -0.06
    æĭŃ
    -0.06
    erra
    -0.06
     Heard
    -0.06
    POSITIVE LOGITS
    裳
    0.08
    üss
    0.08
    YRO
    0.08
    akil
    0.08
    orthand
    0.07
    ikin
    0.07
    æ´Ľä¼Ĭ
    0.07
    Reporting
    0.07
    hest
    0.07
    avier
    0.07
    Activations Density 0.001%

    No Known Activations