© 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. 9944
    Prev
    Next
    INDEX
    Explanations

    actual vs expected

    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
    æħ·
    -0.09
    ailer
    -0.08
    ืà¹Īà¸Ńà¸ĩ
    -0.08
    =sys
    -0.08
    íĤ¹
    -0.08
    noz
    -0.08
    Ùħاس
    -0.08
    eeee
    -0.07
    áŀĶáŁĭ
    -0.07
    cak
    -0.07
    POSITIVE LOGITS
     actual
    0.16
    å®ŀéĻħ
    0.16
    actual
    0.16
    Actual
    0.14
     Actual
    0.14
    å®ŀéĻħçļĦ
    0.14
    _actual
    0.13
    çļĦå®ŀéĻħ
    0.13
    實éļĽ
    0.12
    å®ŀéĻħæĥħåĨµ
    0.12
    Activations Density 0.048%

    No Known Activations