© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    singlet, octet, bond, triplet

    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
    èĭ±å§¿
    -0.08
    ledged
    -0.08
    .live
    -0.07
    ä¸įçĪ½
    -0.07
     managed
    -0.07
    entos
    -0.07
    ãģ¨ãģĨ
    -0.07
    ountain
    -0.07
     ranh
    -0.07
    éºĵ
    -0.07
    POSITIVE LOGITS
    æŀ¯
    0.07
    ä¸ĩå¹´
    0.07
    Ùģت
    0.07
    avno
    0.07
     wholes
    0.07
    abe
    0.07
    quina
    0.07
    adio
    0.07
    åĽ¢
    0.07
    apel
    0.07
    Activations Density 0.002%

    No Known Activations