© 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. 18902
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by casual speech

    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
    åīįäºĶ
    -0.07
    该åĨħ容
    -0.07
    åħ¶äºº
    -0.07
    lando
    -0.07
    llib
    -0.06
     rato
    -0.06
    éĢĤé¾Ħ
    -0.06
    _ports
    -0.06
    .Designer
    -0.06
    stv
    -0.06
    POSITIVE LOGITS
    enius
    0.09
    ÑĥÑģÑĤа
    0.08
    ä¸Ģæī¹
    0.07
    en
    0.07
    æĺĤ
    0.07
    xef
    0.07
    oter
    0.06
    å°ıçģ«
    0.06
    forcer
    0.06
    å°ıéĽª
    0.06
    Activations Density 0.001%

    No Known Activations