© 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. 18226
    Prev
    Next
    INDEX
    Explanations

    Young diagram

    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
     Woodward
    -0.08
    avers
    -0.08
    udara
    -0.07
    klink
    -0.07
     podr
    -0.06
    å
    -0.06
     potenti
    -0.06
    æĤłæĤł
    -0.06
     kiv
    -0.06
    &o
    -0.06
    POSITIVE LOGITS
     xếp
    0.08
    å½ķçĶ¨
    0.08
    éķľåĥı
    0.07
    é«ĺéĢŁä¸ĭè½½
    0.07
     ladder
    0.07
     tallest
    0.07
     staircase
    0.07
     Informática
    0.07
    _pe
    0.07
    çļĦè§ĦåĪĻ
    0.07
    Activations Density 0.010%

    No Known Activations