© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23157
    Prev
    Next
    INDEX
    Explanations

    ends with -ized, -ing, or is a date/year reference

    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
    viron
    -0.07
    orage
    -0.06
    k
    -0.06
     quad
    -0.06
    iman
    -0.06
    å¿ĥæĢ¥
    -0.06
    åĨ°åĨ»
    -0.06
    æ·±æĢĿ
    -0.05
    —
    -0.05
    лÑİ
    -0.05
    POSITIVE LOGITS
    agio
    0.08
    æŁ
    0.08
    æĻĸ
    0.08
    tui
    0.08
    ä¸ĭåIJĮ
    0.08
    åĥıä½ł
    0.08
    çĨł
    0.08
    éķij
    0.08
    igos
    0.08
    agle
    0.07
    Activations Density 0.269%

    No Known Activations