© 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. 18693
    Prev
    Next
    INDEX
    Explanations

    crust, mantle, plasma, oscillations

    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
    åŃIJåľ¨
    -0.08
    ä»¬åľ¨
    -0.07
    ùi
    -0.07
    butt
    -0.07
    ì±ħ
    -0.07
    ç¹ģå¤ļ
    -0.07
    ิà¹īà¸ĩ
    -0.06
     nors
    -0.06
    ##_
    -0.06
     ÑĥÑģÑĤа
    -0.06
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.10
    交çķĮå¤Ħ
    0.10
    -dominated
    0.09
    åĨħçļĦ
    0.09
    æ·±å¤ĦçļĦ
    0.09
    éĩĮçļĦ
    0.08
    åĴĮä¸Ń
    0.08
    å±ĤçļĦ
    0.08
    -wide
    0.08
    å±Ĥ
    0.08
    Activations Density 0.066%

    No Known Activations