© 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. 28275
    Prev
    Next
    INDEX
    Explanations

    remaining amounts/quantities

    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
     itself
    -0.10
    am
    -0.08
    åħ¶åİŁåĽł
    -0.07
    æīĢåľ¨åľ°
    -0.07
    æľ¬èº«çļĦ
    -0.07
    ady
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    iest
    -0.07
    abra
    -0.07
    vert
    -0.07
    POSITIVE LOGITS
    remaining
    0.08
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
    most
    0.08
    -most
    0.08
    ä¸įå¤ļçļĦ
    0.08
    æŶéĹ´éĩĮ
    0.07
    ê²ĥ
    0.07
    å±Ĭä¸ŃåĽ½
    0.07
    OrDefault
    0.07
     обÑģÑĤоÑı
    0.07
    Activations Density 0.011%

    No Known Activations