© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    .Builder, receive, .Request, .selectAll

    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
    obe
    -0.07
    __))
    -0.07
    èĢĮå·²
    -0.07
    马è¹Ħ
    -0.07
    ibbon
    -0.06
    ropole
    -0.06
    mos
    -0.06
    aea
    -0.06
    _strerror
    -0.06
    æľįä»İ
    -0.06
    POSITIVE LOGITS
    ().
    0.08
    éĻħ
    0.08
    aign
    0.08
    åĩĮäºij
    0.07
    leigh
    0.07
     ×ŀ×Ĵ
    0.07
    è¢Ń
    0.07
    å¾ĭå·±
    0.07
    æļĹæ²ī
    0.07
     //.
    0.07
    Activations Density 0.527%

    No Known Activations