© 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. 46110
    Prev
    Next
    INDEX
    Explanations

    absolute value and magnitude

    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
    (es
    -0.08
    eldorf
    -0.08
    chini
    -0.08
    ÑĥÑİ
    -0.07
    chal
    -0.07
    çļĦæ²¹
    -0.07
    chien
    -0.07
    lobal
    -0.07
    ional
    -0.07
    elaar
    -0.07
    POSITIVE LOGITS
    ège
    0.08
    å·¥ä½ľçļĦéĩįè¦ģ
    0.08
    ezu
    0.07
    ë§ĪìŀIJ
    0.07
    indruck
    0.07
    ÑģÑĮ
    0.07
    cus
    0.07
    ë¦Ħ
    0.07
    gur
    0.07
    ůst
    0.07
    Activations Density 0.005%

    No Known Activations