© 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. 33509
    Prev
    Next
    INDEX
    Explanations

    changes in composition, behavior, or status

    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
    æĢ§å¼º
    -0.08
    oland
    -0.07
    issi
    -0.07
    æĢ§èĥ½å¥½
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    强度é«ĺ
    -0.07
    олÑĮÑĪ
    -0.07
     tản
    -0.07
    atti
    -0.07
    å°ıåŃIJ
    -0.06
    POSITIVE LOGITS
    以éĢĤåºĶ
    0.10
     fortunes
    0.09
    æĺ¯çĶ±äºİ
    0.08
    èĢĮå¼ķèµ·
    0.08
     drast
    0.08
     caused
    0.08
     пÑĥÑĤем
    0.08
     drastically
    0.08
    æķ°ä»¥
    0.08
    .Change
    0.08
    Activations Density 0.320%

    No Known Activations