© 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. 20705
    Prev
    Next
    INDEX
    Explanations

    credit and deductions

    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
    ÕŃ
    -0.08
    ulli
    -0.07
     Perspekt
    -0.07
    aidu
    -0.07
    rophy
    -0.07
    æĶ¾è¿ĩ
    -0.06
    åĥļ
    -0.06
     ostr
    -0.06
    ardin
    -0.06
    ноп
    -0.06
    POSITIVE LOGITS
    æĬµæ¶Ī
    0.12
    æĬµæī£
    0.12
    åĩı
    0.11
    æĬµ
    0.11
    æİī
    0.10
    æ¸Ľ
    0.10
    æİīçļĦ
    0.09
     deductions
    0.09
    è¡¡
    0.09
     canc
    0.08
    Activations Density 0.029%

    No Known Activations