© 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. 7472
    Prev
    Next
    INDEX
    Explanations

    version, virtual, matrices, nums, N

    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
    æķ´
    -0.07
    åIJĭ
    -0.06
    æľªæĽ¾
    -0.06
    áĥĺáĥ¢
    -0.06
    çĴ
    -0.06
    ´Ģ
    -0.06
     tá»ij
    -0.06
    äl
    -0.06
    ãģĭãģªãģĭãģ£ãģŁ
    -0.06
    zs
    -0.06
    POSITIVE LOGITS
    _version
    0.08
    Version
    0.08
    çīĪæľ¬çļĦ
    0.08
    .Version
    0.08
    funcs
    0.08
    /version
    0.08
    -version
    0.08
     '{$
    0.08
    ugat
    0.08
    antro
    0.07
    Activations Density 0.008%

    No Known Activations