© 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. 32191
    Prev
    Next
    INDEX
    Explanations

    where you are

    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
     Sale
    -0.07
    emek
    -0.07
    ÙĪØ·
    -0.07
    ilor
    -0.06
     Mati
    -0.06
    å®Ŀå®Ŀ们
    -0.06
    vorg
    -0.06
    åĴļ
    -0.06
    _dims
    -0.06
     units
    -0.06
    POSITIVE LOGITS
    两å¤Ħ
    0.08
    å¦ĤæѤ
    0.08
    —with
    0.08
    usse
    0.07
    éĵģå¡Ķ
    0.07
    ä¿¡
    0.07
    çĥŁçģ«
    0.07
    è¾ľè´Ł
    0.07
    æѤå¤Ħ
    0.07
    åħįå¾Ĺ
    0.07
    Activations Density 0.003%

    No Known Activations