© 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. 21959
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    .sul
    -0.07
    бол
    -0.07
     synerg
    -0.06
    æģ©æĸ¯
    -0.06
    以赴
    -0.06
    uman
    -0.06
    ikat
    -0.06
    æłª
    -0.06
    -lat
    -0.06
    æѧ
    -0.06
    POSITIVE LOGITS
    缸å½ĵäºİ
    0.09
    roach
    0.08
    å¾Ħ缴
    0.08
    æį¢è¨Ģä¹ĭ
    0.08
    _sep
    0.07
    纯粹
    0.07
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.07
    ç´
    0.07
    å°±çĽ¸å½ĵäºİ
    0.07
    opoulos
    0.07
    Activations Density 0.009%

    No Known Activations