© 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. 31216
    Prev
    Next
    INDEX
    Explanations

    I was

    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
    åħĥçļĦ
    -0.07
    ائÙĦ
    -0.07
    éĢģä½ł
    -0.07
    abez
    -0.07
    æĢģ度åĴĮ
    -0.07
    isode
    -0.06
    åĵij
    -0.06
    utton
    -0.06
    æµ·çıł
    -0.06
    otive
    -0.06
    POSITIVE LOGITS
    èĢĢ
    0.09
    åıªæľīèĩªå·±
    0.08
    è¿İæĺ¥
    0.07
    ehn
    0.07
     coloni
    0.07
    <<<<<<<
    0.07
    noc
    0.07
    YO
    0.07
    isma
    0.07
    JB
    0.07
    Activations Density 0.001%

    No Known Activations