© 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. 23565
    Prev
    Next
    INDEX
    Explanations

    numbers following commas

    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
    oz
    -0.08
    ariah
    -0.08
    araf
    -0.08
    aten
    -0.08
    WithName
    -0.07
    ish
    -0.07
    .ie
    -0.07
    abora
    -0.07
    èĢĮå¦Ĥä»Ĭ
    -0.07
    onis
    -0.07
    POSITIVE LOGITS
    rogen
    0.07
    pest
    0.06
    ness
    0.06
    _SCAN
    0.06
    모
    0.06
    apos
    0.06
    ponent
    0.06
    iever
    0.06
    ÑģовеÑģÑĤ
    0.06
    ë¦ĩ
    0.06
    Activations Density 0.012%

    No Known Activations