© 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. 20926
    Prev
    Next
    INDEX
    Explanations

    angular and apparent resolution

    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
    å´ĩå°ļ
    -0.07
    named
    -0.07
     tendencies
    -0.07
    ino
    -0.07
    ÑģоÑģ
    -0.07
    éĹ·
    -0.07
    橱
    -0.07
     dessus
    -0.07
     sacr
    -0.06
    htm
    -0.06
    POSITIVE LOGITS
     distant
    0.09
    çĦ¦è·Ŀ
    0.08
    åĴ«å°º
    0.08
    GetObject
    0.08
    æ¸ħæĻ°åº¦
    0.08
    è¿ľå¤ĦçļĦ
    0.07
    è¿ľè·Ŀ离
    0.07
    è¿ľæĻ¯
    0.07
    åľ¨å½ĵåľ°
    0.07
    大å°ıçļĦ
    0.07
    Activations Density 0.004%

    No Known Activations