© 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. 55893
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and punctuation

    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
    anz
    -0.07
    åĮħ
    -0.07
    è¡£
    -0.07
    ichel
    -0.07
    ä¹Ī
    -0.07
    anzia
    -0.07
    omin
    -0.06
    áĥķáĥĶ
    -0.06
    ä½ķåľ¨
    -0.06
     limp
    -0.06
    POSITIVE LOGITS
    第äºĮç§į
    0.08
    第ä¸ī个
    0.07
    åħĭæŀĹ
    0.07
    第ä¸īç§į
    0.07
    æµ·æ¶Ľ
    0.07
    æĮģç»Ńåıijå±ķ
    0.07
    æī¹åĩĨçļĦé¡¹çĽ®
    0.07
    anski
    0.07
    ÙĪاÙħ
    0.07
    Åijd
    0.07
    Activations Density 0.832%

    No Known Activations