© 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. 24956
    Prev
    Next
    INDEX
    Explanations

    alternative options

    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
     Hamp
    -0.07
    te
    -0.07
    å¤ļåįĬ
    -0.06
    estro
    -0.06
    åĩłä¹İæīĢæľīçļĦ
    -0.06
    عÙĦÙĬ
    -0.06
    ETCH
    -0.06
    ç¿
    -0.06
    大å¤ļæĺ¯
    -0.06
    åľ¨ä»¥åIJİ
    -0.06
    POSITIVE LOGITS
     alternatives
    0.22
     alternative
    0.21
     Alternative
    0.20
    alternative
    0.20
    Alternative
    0.19
     alternativa
    0.18
     Altern
    0.18
     alternativ
    0.18
     alternatif
    0.18
     alternativas
    0.18
    Activations Density 0.284%

    No Known Activations