© 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. 56278
    Prev
    Next
    INDEX
    Explanations

    code strings and html

    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
    ettino
    -0.08
    éħİ
    -0.08
    entina
    -0.08
     META
    -0.08
    話說
    -0.08
    _cpu
    -0.07
     âĵĺ
    -0.07
    atorium
    -0.07
    ä½ľæ³ķ
    -0.07
    عث
    -0.07
    POSITIVE LOGITS
    bund
    0.07
    ä¸Ģåĩº
    0.06
    iep
    0.06
    иÑģÑĮ
    0.06
    ä¸ļ
    0.06
    jes
    0.06
    çĶ¸
    0.06
    ä»Ķ
    0.06
    éĤij
    0.06
    iken
    0.06
    Activations Density 0.063%

    No Known Activations