© 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. 42148
    Prev
    Next
    INDEX
    Explanations

    documentation titles

    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
    avax
    -0.08
    reece
    -0.07
    ØŃÙĦ
    -0.07
    æļ§
    -0.06
    lasses
    -0.06
    xffffff
    -0.06
    å³¥åµĺ
    -0.06
    onom
    -0.06
    atap
    -0.06
    ledi
    -0.06
    POSITIVE LOGITS
    asang
    0.08
    ijt
    0.08
    æ±²
    0.07
    okin
    0.07
    åk
    0.07
    strup
    0.07
    allery
    0.07
     artig
    0.07
    åĪĨ许
    0.07
    ckte
    0.07
    Activations Density 0.122%

    No Known Activations