© 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. 2105
    Prev
    Next
    INDEX
    Explanations

    sacrifice, sin, pleasure, self

    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
    å¾·éŁ³
    -0.07
     reportedly
    -0.07
    hausen
    -0.07
    æĽ´å¤ļåĽŀçŃĶ
    -0.07
    æľŃ
    -0.07
    sic
    -0.07
    æĴ°æĸĩ
    -0.07
    æľªæĮīè§Ħå®ļ
    -0.06
    ences
    -0.06
    åħ¨éĻ¢
    -0.06
    POSITIVE LOGITS
     fucked
    0.08
    çĸĨ
    0.07
     tremendous
    0.07
     billions
    0.07
    è¿Ļä¸ªä¸ľè¥¿
    0.07
    被åĪ«äºº
    0.07
     shitty
    0.07
    æijĦåıĸ
    0.07
    unkt
    0.07
    交åĪ°
    0.07
    Activations Density 0.051%

    No Known Activations