© 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. 51033
    Prev
    Next
    INDEX
    Explanations

    settlement or knot resolution

    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
    åħ¼æĢ»ç»ıçIJĨ
    -0.10
    ities
    -0.09
    er
    -0.08
    erweise
    -0.08
    keit
    -0.08
    erge
    -0.08
    erin
    -0.08
    ality
    -0.08
    iscal
    -0.08
    żej
    -0.07
    POSITIVE LOGITS
    ation
    0.10
    imated
    0.09
    ì§ĵ
    0.08
    apsed
    0.08
    agger
    0.08
    à§Ģয়
    0.08
    imating
    0.08
    halb
    0.08
    ablish
    0.08
    ÙijÙī
    0.08
    Activations Density 0.009%

    No Known Activations