© 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. 45964
    Prev
    Next
    INDEX
    Explanations

    following "flee" or "Release"

    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
    çŃīåİŁåĽł
    -0.08
    å°±æѤ
    -0.08
    çŃīæĥħåĨµ
    -0.07
    اÙħ
    -0.07
    PA
    -0.07
    HP
    -0.07
    å¹´æľĪ
    -0.07
    çŃīéĹ®é¢ĺ
    -0.07
    ight
    -0.06
     alike
    -0.06
    POSITIVE LOGITS
    ownie
    0.08
    ä½łä¸Ģ个
    0.07
     inilah
    0.07
    çľ¼çĿģçĿģ
    0.07
    .trailing
    0.06
    æł¹æį®ä¸ªäºº
    0.06
    天å®ĩ
    0.06
    .ta
    0.06
    èĩªå°Ĭå¿ĥ
    0.06
    æł¹æį®ä¸įåIJĮçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations