© 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. 56238
    Prev
    Next
    INDEX
    Explanations

    lowering or lowered

    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
    ness
    -0.11
    haber
    -0.09
    agher
    -0.09
    lete
    -0.09
    ständig
    -0.08
    ullah
    -0.08
    kali
    -0.08
    ota
    -0.08
    éķ¿åľ¨
    -0.08
    å£Į
    -0.07
    POSITIVE LOGITS
     diri
    0.09
     Diri
    0.08
    lew
    0.07
    à¦ĩ
    0.07
    Ñİ
    0.07
    йда
    0.07
     Sabha
    0.07
    ĵ
    0.07
    ĥ
    0.07
    ķ
    0.07
    Activations Density 0.002%

    No Known Activations