© 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. 39838
    Prev
    Next
    INDEX
    Explanations

    importance percentage sales fraction

    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
    зей
    -0.06
    _RENDER
    -0.06
     enlarg
    -0.06
    erset
    -0.06
    è
    -0.06
    зли
    -0.06
    боÑĢ
    -0.06
    åĸľéĹ»
    -0.06
    åı¯ç¬ij
    -0.06
    é¦ĸèµŀ
    -0.06
    POSITIVE LOGITS
    -weight
    0.12
     weighting
    0.12
    åįłæĢ»
    0.11
     weight
    0.11
    weight
    0.11
    æĿĥéĩį
    0.10
     веÑģа
    0.10
    æ¯Ķéĩį
    0.10
    _weight
    0.10
    _weights
    0.10
    Activations Density 0.020%

    No Known Activations