© 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. 16065
    Prev
    Next
    INDEX
    Explanations

    public class

    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
     cour
    -0.06
    elf
    -0.06
    izer
    -0.06
    ë£Į
    -0.06
    enes
    -0.06
    onese
    -0.06
    åİķ
    -0.06
    rijf
    -0.06
    isoft
    -0.06
     lev
    -0.06
    POSITIVE LOGITS
    ancock
    0.08
    ç¯ĩä¸ī
    0.08
    idang
    0.07
    strup
    0.07
    voke
    0.07
    byn
    0.07
    chter
    0.07
    kopf
    0.07
    arness
    0.07
    工夫
    0.07
    Activations Density 0.211%

    No Known Activations