© 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. 51135
    Prev
    Next
    INDEX
    Explanations

    Manhattan College

    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
     Poli
    -0.06
    онаÑĤ
    -0.06
     bulk
    -0.06
     avg
    -0.06
    £
    -0.06
    æĹłæĥħçļĦ
    -0.06
    计
    -0.06
    æĢİ
    -0.06
    人为
    -0.06
     Le
    -0.06
    POSITIVE LOGITS
    夷
    0.08
    ucha
    0.08
    angkat
    0.08
    viv
    0.07
     Luar
    0.07
    ialog
    0.07
    åıĹæķĻèĤ²
    0.07
    angkatan
    0.07
    åºĶèģĺ人åijĺ
    0.07
    rière
    0.07
    Activations Density 0.001%

    No Known Activations