© 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. 33529
    Prev
    Next
    INDEX
    Explanations

    ideal followed by related suffixes

    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
    Ïģικ
    -0.09
    ê¹IJ
    -0.08
    elier
    -0.08
    engel
    -0.08
    elsea
    -0.08
    åįģ大åĵģçīĮ
    -0.08
    alité
    -0.08
    äºĭçļĦ
    -0.08
    езд
    -0.08
    کر
    -0.08
    POSITIVE LOGITS
    ized
    0.13
    erweise
    0.11
    izing
    0.10
    -looking
    0.10
    ization
    0.10
    åĮĸçļĦ
    0.09
    istically
    0.09
    æĢ§åľ°
    0.09
    istic
    0.09
    æĢ§çļĦ
    0.08
    Activations Density 0.012%

    No Known Activations