© 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. 63380
    Prev
    Next
    INDEX
    Explanations

    random or randomly generating things

    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
    æĹłéĿŀ
    -0.07
    è£
    -0.07
    .download
    -0.07
    abel
    -0.07
    éĻįè´¹
    -0.07
    å®ľæĺ¥
    -0.06
    imbra
    -0.06
     Hurt
    -0.06
    缩éĩı
    -0.06
     analy
    -0.06
    POSITIVE LOGITS
    .rand
    0.09
     random
    0.09
     randomly
    0.09
    random
    0.08
    -random
    0.08
    éļıæľº
    0.08
     randomness
    0.08
    =random
    0.08
    .random
    0.08
    .Random
    0.08
    Activations Density 0.052%

    No Known Activations