© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21769
    Prev
    Next
    INDEX
    Explanations

    number 1 introductory point

    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
    ichi
    -0.07
     mah
    -0.07
    emaal
    -0.07
    Leaks
    -0.07
    åħļçļĦ群ä¼Ĺ路线
    -0.07
    áĥIJáĥ®
    -0.06
     chances
    -0.06
    antie
    -0.06
    arters
    -0.06
    è°į
    -0.06
    POSITIVE LOGITS
    pread
    0.08
    ÑģÑĤина
    0.07
    éĻµåĽŃ
    0.07
    YZ
    0.07
     ActiveSupport
    0.07
    วว
    0.07
     Lain
    0.07
    esm
    0.07
    HIP
    0.07
    orz
    0.07
    Activations Density 0.001%

    No Known Activations