© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32936
    Prev
    Next
    INDEX
    Explanations

    .html links or documentation references

    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
    ertest
    -0.08
    PFN
    -0.07
    /antlr
    -0.07
    ICH
    -0.07
    ÙĤÙĬÙĤ
    -0.07
     Catar
    -0.07
    otos
    -0.07
    /stretchr
    -0.07
    (`/
    -0.07
    _ctor
    -0.07
    POSITIVE LOGITS
    #.
    0.08
    %E
    0.08
    âĢİ
    0.08
    %C
    0.07
    .html
    0.07
    &type
    0.07
    anderia
    0.07
    #!
    0.06
    overview
    0.06
    åĭ¤æģ³
    0.06
    Activations Density 0.277%

    No Known Activations