© 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. 51383
    Prev
    Next
    INDEX
    Explanations

    series formulas and calculations

    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
    Probe
    -0.08
    å®ŀå¤Ħ
    -0.08
    ivio
    -0.08
    onese
    -0.08
    ancar
    -0.08
    å¼ĢåĪ°
    -0.07
     ÙĪاÙĦعÙħÙĦ
    -0.07
    _cmds
    -0.07
    å°ıæłij
    -0.07
    oice
    -0.07
    POSITIVE LOGITS
    adh
    0.08
    ableView
    0.08
    æĸ¯åĿ¦
    0.07
    éħįå¥ĹçļĦ
    0.07
    ngo
    0.06
    åĪ©æ°ij
    0.06
     Sussex
    0.06
    (TM
    0.06
     sudo
    0.06
    _trim
    0.06
    Activations Density 0.001%

    No Known Activations