© 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. 57189
    Prev
    Next
    INDEX
    Explanations

    group theory, algebra, or specific domains

    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
    UFFIX
    -0.09
    ACHE
    -0.08
    egner
    -0.08
    errer
    -0.08
    以任ä½ķ
    -0.08
     اÙĨع
    -0.08
    ereco
    -0.08
    REN
    -0.08
    ren
    -0.07
    arjo
    -0.07
    POSITIVE LOGITS
     Cri
    0.07
    enga
    0.07
    xy
    0.06
     cri
    0.06
    ette
    0.06
    (xy
    0.06
    ä¸ī
    0.06
     dik
    0.06
     Libert
    0.06
    é§
    0.06
    Activations Density 0.006%

    No Known Activations