© 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. 45083
    Prev
    Next
    INDEX
    Explanations

    dimensional or dimension related to rank

    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
    okr
    -0.08
    大æĬĬ
    -0.08
     Cage
    -0.08
    oten
    -0.08
     combined
    -0.07
    ocking
    -0.07
     cage
    -0.07
    _reverse
    -0.07
    å¹»å¢ĥ
    -0.07
    uhi
    -0.07
    POSITIVE LOGITS
    -dimensional
    0.09
    dimension
    0.08
    å®ŀä½ĵ
    0.08
     dimension
    0.08
    Dimension
    0.08
     dimensional
    0.08
    维度
    0.07
    ç¶Ń
    0.07
     Dim
    0.07
    ç»´
    0.07
    Activations Density 0.010%

    No Known Activations