© 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. 60123
    Prev
    Next
    INDEX
    Explanations

    dependence, temperature, ratio, node, release

    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
    oplan
    -0.08
    roy
    -0.08
    ainless
    -0.08
    å°
    -0.07
    æķ¢è¯´
    -0.07
    oref
    -0.07
    pecting
    -0.07
    raz
    -0.07
    Įĵ
    -0.07
    ore
    -0.07
    POSITIVE LOGITS
    纪
    0.07
    udo
    0.07
    onus
    0.06
    æģ¯
    0.06
    ÙĪارÙĩ
    0.06
    onato
    0.06
    tti
    0.06
    lon
    0.06
    ×ķת
    0.06
    alt
    0.06
    Activations Density 0.501%

    No Known Activations