© 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. 8839
    Prev
    Next
    INDEX
    Explanations

    inverse of fractions or numbers

    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
    cano
    -0.07
    .extend
    -0.07
    udge
    -0.07
    å¡ĺ
    -0.07
    alang
    -0.07
    ä¸įæĶ¾
    -0.06
    براÙĨ
    -0.06
    ged
    -0.06
    wal
    -0.06
    ained
    -0.06
    POSITIVE LOGITS
    loff
    0.07
    esson
    0.07
    beer
    0.07
    act
    0.07
    驼
    0.07
    客
    0.06
    ideon
    0.06
    efeller
    0.06
    oser
    0.06
    rotn
    0.06
    Activations Density 0.005%

    No Known Activations