© 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. 7761
    Prev
    Next
    INDEX
    Explanations

    scores like 6–7

    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
    åįĥç§ĭ
    -0.06
    
    -0.06
    å°½
    -0.06
     Sure
    -0.06
    ika
    -0.06
    indak
    -0.06
    åįī
    -0.06
     Asamblea
    -0.06
    owers
    -0.05
     opposed
    -0.05
    POSITIVE LOGITS
    eri
    0.10
    bage
    0.08
     rao
    0.08
    erin
    0.08
     vibrator
    0.08
    erce
    0.07
    oned
    0.07
     geler
    0.07
    .optimize
    0.07
    رÙĪÙĬ
    0.07
    Activations Density 0.002%

    No Known Activations