© 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. 47447
    Prev
    Next
    INDEX
    Explanations

    long-term effects

    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
    ions
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    渡åģĩ
    -0.07
    è°¤
    -0.07
    ä¸įå¾ĹäºĨ
    -0.07
    IONS
    -0.06
    ãĤ¸ãĥĥãĥĪ
    -0.06
    aces
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.06
    POSITIVE LOGITS
    etime
    0.08
    onge
    0.08
    âĢij
    0.07
    /*/
    0.07
    ê¸ī
    0.07
    portun
    0.07
    ìĭľê°Ħ
    0.07
    âĢIJ
    0.07
    uite
    0.07
    å¾ĭå¸ĪäºĭåĬ¡æīĢå¾ĭå¸Ī
    0.07
    Activations Density 0.384%

    No Known Activations