© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    quantum occupation number

    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
    adre
    -0.08
    ار
    -0.07
    ascar
    -0.07
    æĸĭ
    -0.07
     oil
    -0.07
    agnol
    -0.06
    泪æµģ
    -0.06
    çŁ³æ²¹
    -0.06
    æ²¹çĶ°
    -0.06
    æµijçĦ¶
    -0.06
    POSITIVE LOGITS
    ingo
    0.08
    antum
    0.08
    ighton
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
    ConnectionFactory
    0.08
    ivia
    0.08
     disemb
    0.07
    amat
    0.07
    ablish
    0.07
    ursors
    0.07
    Activations Density 0.004%

    No Known Activations