© 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. 57370
    Prev
    Next
    INDEX
    Explanations

    converting html strings to original form

    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
    estad
    -0.08
    anta
    -0.07
    },{"
    -0.07
    olley
    -0.07
    éĻIJ
    -0.06
    baran
    -0.06
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    -0.06
    oth
    -0.06
    èĻ
    -0.06
     SetUp
    -0.06
    POSITIVE LOGITS
    åİŁæĿ¥æĺ¯
    0.09
     Original
    0.09
     original
    0.09
     originales
    0.09
    Original
    0.08
    _original
    0.08
    åİŁ
    0.08
    åİŁä»¶
    0.08
     originals
    0.08
     originale
    0.08
    Activations Density 0.148%

    No Known Activations