© 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. 57517
    Prev
    Next
    INDEX
    Explanations

    legal case names

    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
    å¯ĴåĨ°
    -0.07
    %B
    -0.07
    oja
    -0.07
    æĽ´æ²¡æľī
    -0.06
    roz
    -0.06
    ãģ¨ãĤĤãģ«
    -0.06
    åħ±ãģ«
    -0.06
    é¡¹çĽ®åıĬ
    -0.06
    åħĭæĸ¯
    -0.06
    &quot
    -0.06
    POSITIVE LOGITS
     vs
    0.20
     versus
    0.19
    _vs
    0.15
    vs
    0.15
    -vs
    0.14
     âĨĶ
    0.12
     Vs
    0.12
    âĨĴ
    0.12
     <->
    0.11
    ä¸İçݰ代
    0.11
    Activations Density 0.620%

    No Known Activations