© 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. 9515
    Prev
    Next
    INDEX
    Explanations

    ARG commands

    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
    è¿ijæĪĺ
    -0.07
    leit
    -0.06
    çļĦçݰ代
    -0.06
    جر
    -0.06
    quisites
    -0.06
     NastÄĻp
    -0.06
    utama
    -0.06
    Compound
    -0.06
    å²Ĥ
    -0.05
    emberg
    -0.05
    POSITIVE LOGITS
    zion
    0.08
    adis
    0.08
    lds
    0.08
    ä¸īæĸ¹
    0.08
    æĨ¬
    0.08
    egos
    0.07
    anski
    0.07
    èī²åĪĹ
    0.07
    aries
    0.07
    deaux
    0.07
    Activations Density 0.424%

    No Known Activations