© 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. 3947
    Prev
    Next
    INDEX
    Explanations

    discriminants, fingerprints, ois, sigma, suite

    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
    adak
    -0.08
    ban
    -0.08
    顺é£İ
    -0.08
    åIJ¾
    -0.08
    alsy
    -0.07
    è¦Ĩ
    -0.07
    etil
    -0.07
    ky
    -0.07
    ibi
    -0.07
     inplace
    -0.07
    POSITIVE LOGITS
     invariant
    0.07
    elar
    0.07
    äºĮåįģä¸ĥ
    0.06
    Ĵ
    0.06
    ä¸įåıĺ
    0.06
     feu
    0.06
    é¢ĦèѦ
    0.06
    马æĭī
    0.06
    Invariant
    0.06
    Ķ
    0.06
    Activations Density 0.001%

    No Known Activations