© 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. 57273
    Prev
    Next
    INDEX
    Explanations

    positive or negative impact

    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
    essel
    -0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    -0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.07
    irut
    -0.07
    说äºĨç®Ĺ
    -0.07
    heimer
    -0.06
    羣æŃ£åľ°
    -0.06
    åĴ¨è¯¢çĶµè¯Ŀ
    -0.06
    igny
    -0.06
    éĢļåĪĻ
    -0.06
    POSITIVE LOGITS
    roll
    0.08
    ativamente
    0.08
    ious
    0.08
    /help
    0.08
     ÑģÑĤоÑĢона
    0.08
    å±ħå¤ļ
    0.08
    жел
    0.07
    uzion
    0.07
    ç¥ŀçİĭ
    0.07
    åIJij好
    0.07
    Activations Density 0.141%

    No Known Activations