© 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. 41684
    Prev
    Next
    INDEX
    Explanations

    Category: or template:

    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¯Ĵé£İ
    -0.07
    ä¸į容
    -0.06
    illi
    -0.06
    گاÙĨ
    -0.06
     Bre
    -0.06
    åIJ«ç³Ĭ
    -0.06
    anium
    -0.06
    å¤Ħ
    -0.06
    éĻ¤æģ¶
    -0.06
    æ¼ĵ
    -0.06
    POSITIVE LOGITS
    åħ¶äºº
    0.09
    anima
    0.08
     Tomorrow
    0.08
    lide
    0.07
    മാ
    0.07
    ombat
    0.07
     "></
    0.07
    ä¸ĢåĽ½
    0.07
     collaps
    0.07
    forme
    0.07
    Activations Density 0.021%

    No Known Activations