© 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. 40261
    Prev
    Next
    INDEX
    Explanations

    function calligraphy name

    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
    leur
    -0.08
    AINS
    -0.08
    ohl
    -0.08
    quil
    -0.08
    uari
    -0.08
    itters
    -0.08
    Ĥ¬
    -0.07
    ÙİÙijØ°
    -0.07
    borg
    -0.07
    ĵĴ
    -0.07
    POSITIVE LOGITS
    erg
    0.06
    erm
    0.06
    ä¸įçŁ¥éģĵä½ł
    0.06
    åĪĨä¸įæ¸ħ
    0.06
    殿
    0.06
    erei
    0.06
    avis
    0.06
    rix
    0.06
     íķ©
    0.06
    两æĢ§
    0.06
    Activations Density 0.001%

    No Known Activations