© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42311
    Prev
    Next
    INDEX
    Explanations

    recommendations or advice

    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
    æ¦Ľ
    -0.07
     outs
    -0.07
    elter
    -0.07
    ä½Ľ
    -0.06
    娴
    -0.06
    æĥŁ
    -0.06
    å¾Ĺ人
    -0.06
    å¤ĸ
    -0.06
    apun
    -0.06
    estring
    -0.06
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.15
     other
    0.15
    åħ¶ä»ĸ
    0.14
    åħ¶ä»ĸçļĦ
    0.14
    åħ¶å®ĥçļĦ
    0.13
    æľīåħ¶ä»ĸ
    0.13
    other
    0.13
    åĪ«çļĦ
    0.13
    è¿ĺæľīåħ¶ä»ĸ
    0.13
    åħ¶å®ĥ
    0.12
    Activations Density 0.370%

    No Known Activations