© 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. 9825
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by assignments or formulas

    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
    ery
    -0.07
    å±±éķĩ
    -0.07
    å¿ĥ缮ä¸ŃçļĦ
    -0.07
    æŀģäºĨ
    -0.06
    å½ĵä¸ŃçļĦ
    -0.06
    -p
    -0.06
    inator
    -0.06
    çĽĽå¤§çļĦ
    -0.06
    è¿Ļç§įçݰ象
    -0.06
    masters
    -0.06
    POSITIVE LOGITS
    æss
    0.08
    nda
    0.08
    ().'/
    0.08
    nable
    0.08
    ogui
    0.08
    ncy
    0.07
    _HOOK
    0.07
    rastructure
    0.07
    å»·
    0.07
    urada
    0.07
    Activations Density 0.005%

    No Known Activations