© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20649
    Prev
    Next
    INDEX
    Explanations

    itself, fine, understandable, good

    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
    .hu
    -0.07
    iddel
    -0.07
    otor
    -0.07
    riba
    -0.06
    οÏĤ
    -0.06
    enor
    -0.06
    adah
    -0.06
    crest
    -0.06
    .addTo
    -0.06
    èĽ¾
    -0.06
    POSITIVE LOGITS
    端起
    0.08
    (KP
    0.08
    lia
    0.08
    æĴijèµ·
    0.07
    erring
    0.07
    WithURL
    0.07
    æ¦Ħ
    0.07
    ×ķ×ĺ
    0.07
    被å¥Ĺ
    0.07
    _PM
    0.07
    Activations Density 0.002%

    No Known Activations