© 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. 55389
    Prev
    Next
    INDEX
    Explanations

    quoted phrases

    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
    aldi
    -0.09
    à¤Ĥध
    -0.08
    ifax
    -0.07
    æľ¬å¹³åı°
    -0.07
    niÄį
    -0.07
    ulik
    -0.07
    /]
    -0.07
    ARIANT
    -0.07
    witter
    -0.07
     LayoutInflater
    -0.07
    POSITIVE LOGITS
    ìļ´ëį°
    0.06
     ___
    0.06
    ajs
    0.06
    ica
    0.06
    HT
    0.06
     _____
    0.06
    atos
    0.06
    ict
    0.06
    oner
    0.06
    æįľ
    0.06
    Activations Density 0.028%

    No Known Activations