© 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. 25025
    Prev
    Next
    INDEX
    Explanations

    keep receiving data

    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
    ehme
    -0.09
    er
    -0.08
    åĸľéĹ»
    -0.08
    otra
    -0.08
    ughters
    -0.08
    akil
    -0.08
    erenc
    -0.08
    ä¸ĩä¸Ī
    -0.08
    uale
    -0.08
    ÎŃα
    -0.08
    POSITIVE LOGITS
    alive
    0.10
     gìn
    0.09
    ä¸įä½ı
    0.09
    erv
    0.09
    ä½ıäºĨ
    0.08
    ä½ı
    0.08
    ÑģÑı
    0.08
    éĻIJäºİ
    0.08
    nya
    0.08
     abre
    0.08
    Activations Density 0.040%

    No Known Activations