© 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. 45973
    Prev
    Next
    INDEX
    Explanations

    that can be

    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
     zwar
    -0.12
    èĻ½çĦ¶æ²¡æľī
    -0.12
    èĻ½çĦ¶
    -0.12
     обаÑĩе
    -0.12
    èĻ½çĦ¶åľ¨
    -0.12
     tehát
    -0.12
    èĻ½çĦ¶ä¸įæĺ¯
    -0.11
    éĽĸçĦ¶
    -0.11
     totiž
    -0.10
     Although
    -0.10
    POSITIVE LOGITS
     thereof
    0.11
     daarvan
    0.10
    çĶ¨å®ĥ
    0.09
    å®ĥå°±æĺ¯
    0.09
    å®ĥæĺ¯
    0.09
     it
    0.09
     importantly
    0.08
    ler
    0.08
    ãģĿãĤĮãĤĴ
    0.08
    åħ¶ä¸ŃåĮħæĭ¬
    0.08
    Activations Density 0.285%

    No Known Activations