© 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. 14647
    Prev
    Next
    INDEX
    Explanations

    Integration, Basket, Buyers, Freed

    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
    APAN
    -0.08
    cly
    -0.06
     bare
    -0.06
    onese
    -0.06
    apu
    -0.06
     Viale
    -0.06
    klen
    -0.06
    rl
    -0.06
    anny
    -0.06
    åĢĴä¹Ł
    -0.06
    POSITIVE LOGITS
    اء
    0.08
     ÑĤоже
    0.07
    åĥıåľ¨
    0.07
     cin
    0.07
    ush
    0.07
    cut
    0.07
    hur
    0.07
    @Table
    0.07
    áĥIJáĥ®
    0.07
    داÙĨ
    0.07
    Activations Density 0.360%

    No Known Activations