© 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. 13441
    Prev
    Next
    INDEX
    Explanations

    branching, fractions, and proportions

    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
     Fau
    -0.07
    æĺłåħ¥
    -0.07
     instantiated
    -0.07
    agar
    -0.07
    imeo
    -0.07
     unregister
    -0.07
    ÙĬÙĨØ©
    -0.07
    éļıå¤Ħåı¯è§ģ
    -0.07
    并ä¸įéļ¾
    -0.07
    ADV
    -0.07
    POSITIVE LOGITS
     branching
    0.08
     percentages
    0.08
    çĻ¾åĪĨ
    0.08
     probability
    0.08
     fraction
    0.08
    æĶ¾åĩº
    0.08
    çĻ¾åĪĨæ¯Ķ
    0.08
     probabilities
    0.07
    alternate
    0.07
    åĪĨåĩº
    0.07
    Activations Density 0.010%

    No Known Activations