© 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. 47187
    Prev
    Next
    INDEX
    Explanations

    positive offsets and amounts

    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
    Į¨
    -0.08
    ostar
    -0.07
    >').
    -0.07
    UGHT
    -0.07
    ä¸ĭæĿ¥
    -0.07
    anismos
    -0.07
    ikh
    -0.06
    haupt
    -0.06
    ä¸ĭ称
    -0.06
    éĩįä¸Ńä¹ĭéĩį
    -0.06
    POSITIVE LOGITS
    /-
    0.13
    /+
    0.10
    ,+
    0.09
    /--
    0.09
    tir
    0.08
     (+
    0.07
    ırı
    0.07
    icto
    0.07
    edo
    0.07
    cing
    0.07
    Activations Density 0.032%

    No Known Activations