© 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. 57243
    Prev
    Next
    INDEX
    Explanations

    numbers followed by rounded

    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
    @[
    -0.09
    onium
    -0.09
    optgroup
    -0.08
    æĸ°ç½ij
    -0.08
    nage
    -0.08
    enga
    -0.08
    HEME
    -0.08
    æĬĬäºĭæĥħ
    -0.08
    .writ
    -0.08
    áĭ«
    -0.08
    POSITIVE LOGITS
     (
    0.06
    ç®Ĺæĺ¯
    0.06
     mu
    0.06
    å¦ĸ
    0.06
     N
    0.06
    åĭĴ
    0.06
    avana
    0.06
    cea
    0.06
    ç®Ĺ
    0.05
    åŃ½
    0.05
    Activations Density 0.021%

    No Known Activations