© 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. 8748
    Prev
    Next
    INDEX
    Explanations

    data manipulation and code commands

    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
    dbo
    -0.08
    ession
    -0.08
    @example
    -0.08
     bagni
    -0.07
    家访
    -0.07
    istry
    -0.07
    ä¹IJçļĦ
    -0.07
    oces
    -0.07
    erci
    -0.07
    <|fim_prefix|>
    -0.07
    POSITIVE LOGITS
    ueux
    0.06
     Spears
    0.06
    acht
    0.06
    urie
    0.06
    _tensors
    0.06
    ØŃاÙĦ
    0.06
    交å¾ħ
    0.06
    _definitions
    0.06
    ucs
    0.06
    achinery
    0.06
    Activations Density 0.145%

    No Known Activations