© 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. 45390
    Prev
    Next
    INDEX
    Explanations

    acquire

    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
    jak
    -0.07
    esc
    -0.07
    ulls
    -0.07
    hashed
    -0.07
    à¦Łà§ĩ
    -0.07
    colo
    -0.07
    ember
    -0.06
     Ñģобой
    -0.06
    å¤ļè°¢
    -0.06
    缼ãĤĬ
    -0.06
    POSITIVE LOGITS
    çŁ¥çļĦ
    0.10
    æĽ´å¤ļä¿¡æģ¯
    0.10
    éķ¿è¶³
    0.09
    并使çĶ¨
    0.09
    ãĤĴå¾Ĺ
    0.09
    OrUpdate
    0.08
    梦å¯IJ以æ±Ĥ
    0.08
     rid
    0.08
    /install
    0.08
    /get
    0.08
    Activations Density 0.081%

    No Known Activations