© 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. 44154
    Prev
    Next
    INDEX
    Explanations

    compartments and gradients

    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
    çĶ·çļĦ
    -0.08
    æīŃ
    -0.07
    åıijå±ķä¸Ńå¿ĥ
    -0.07
    诺è¨Ģ
    -0.07
    纯
    -0.07
    ugio
    -0.07
    纽
    -0.07
    uts
    -0.07
    ä½ĻåĬĽ
    -0.07
    à¸Ĺà¸Ńà¸Ķ
    -0.07
    POSITIVE LOGITS
     compartments
    0.09
    -facing
    0.08
    ä¸Ģ侧
    0.08
     compartment
    0.08
    ublic
    0.08
    STACK
    0.07
    åĿIJæĭ¥
    0.07
     concentrations
    0.07
    è¿ľæµģ
    0.07
    bulk
    0.07
    Activations Density 0.034%

    No Known Activations