© 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. 51521
    Prev
    Next
    INDEX
    Explanations

    title separator

    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
    asco
    -0.08
    asu
    -0.08
    æ¬ł
    -0.07
     diserta
    -0.07
    çĶŁç´ł
    -0.07
    ÙĤض
    -0.07
    acco
    -0.07
    iÄį
    -0.07
    roit
    -0.07
    æĺŁæµ·
    -0.07
    POSITIVE LOGITS
    esar
    0.07
    åļ
    0.07
    ftar
    0.06
    yed
    0.06
    aki
    0.06
    fter
    0.06
    å°Ĩä»İ
    0.06
    rasil
    0.06
    æĺ¯åIJ§
    0.06
    çĶ¨è½¦
    0.06
    Activations Density 0.001%

    No Known Activations