© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    peak, stabilize, finalize

    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
    ikke
    -0.07
    adders
    -0.07
     STACK
    -0.07
    uid
    -0.07
    skal
    -0.07
    产åĵģåı¬åĽŀ
    -0.07
    åİŁæľ¬æĺ¯
    -0.06
    èĥĮæĻ¯çļĦ
    -0.06
    æĹłå¤Ħä¸įåľ¨
    -0.06
    伺
    -0.06
    POSITIVE LOGITS
    stable
    0.12
    稳å®ļ
    0.12
     stable
    0.12
    稳å®ļçļĦ
    0.12
     stabilization
    0.12
     stabilize
    0.12
    iteration
    0.11
     stabilized
    0.11
     Stable
    0.11
     stabil
    0.11
    Activations Density 0.030%

    No Known Activations