© 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. 51065
    Prev
    Next
    INDEX
    Explanations

    facts, numbers, disease, Google, copied

    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
    agina
    -0.07
    izza
    -0.07
    æĻĵ举
    -0.07
    éĻIJåĪ¶æĢ§
    -0.07
    ifo
    -0.07
    å§ĭèĩ³
    -0.07
    æł¹æľ¬
    -0.07
    OVER
    -0.06
    åħ
    -0.06
    uard
    -0.06
    POSITIVE LOGITS
     blindly
    0.09
    ciano
    0.08
    éĻĮçĶŁçļĦ
    0.08
     mechanically
    0.07
     formulas
    0.07
    æĽ´æĺ¯ä¸Ģ
    0.07
    utip
    0.07
     apl
    0.07
    aide
    0.07
     labels
    0.06
    Activations Density 0.029%

    No Known Activations