© 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. 63527
    Prev
    Next
    INDEX
    Explanations

    forms ending in ion/ation

    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
     Lec
    -0.07
    imax
    -0.07
    å°½ãģı
    -0.07
    èĨ©
    -0.06
    à¸Ľà¸´
    -0.06
    ennie
    -0.06
    azel
    -0.06
    ä¸Ģè¶Ł
    -0.06
    istou
    -0.06
    loge
    -0.06
    POSITIVE LOGITS
    çĽĪçĽĪ
    0.09
     formed
    0.08
     formation
    0.08
    容åĻ¨ä¸Ń
    0.08
    çĶ³
    0.08
    Formation
    0.07
     charged
    0.07
    交æĬķ
    0.07
     charges
    0.07
     negative
    0.07
    Activations Density 0.004%

    No Known Activations