© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25125
    Prev
    Next
    INDEX
    Explanations

    gamma, ip, mun, xml, iling units

    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
    åģ¥å£®
    -0.07
    Fixture
    -0.07
    èĤ©ä¸Ĭ
    -0.06
    -ajax
    -0.06
    客
    -0.06
    èĬį
    -0.06
    以èĩªå·±
    -0.06
    对æīĢ
    -0.06
    _HAL
    -0.06
    COMMENT
    -0.06
    POSITIVE LOGITS
    anos
    0.08
    åĻ
    0.07
    isky
    0.07
    éŃĶå¹»
    0.07
     swirl
    0.07
    evil
    0.07
     Crack
    0.07
    keyup
    0.07
    æīŃæĽ²
    0.07
    èĢģ头
    0.07
    Activations Density 0.004%

    No Known Activations