© 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. 7441
    Prev
    Next
    INDEX
    Explanations

    digits and character counts

    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±åIJĦ
    -0.09
    suma
    -0.08
    éĴ°
    -0.08
    uzu
    -0.08
     gezi
    -0.08
    ESH
    -0.08
    ernal
    -0.08
    大åѦåŁİ
    -0.08
    soever
    -0.08
    سات
    -0.08
    POSITIVE LOGITS
    ÙĤÙĦ
    0.06
     fr
    0.06
    è¶ħè¶Ĭ
    0.06
    ç®Ĺ
    0.06
    rokes
    0.06
     подÑĢÑıд
    0.06
    å¾Ħ
    0.06
    f
    0.06
     .
    0.05
    ity
    0.05
    Activations Density 0.004%

    No Known Activations