© 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. 25905
    Prev
    Next
    INDEX
    Explanations

    missing things, longing, nostalgia

    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
    ateg
    -0.09
    icolo
    -0.07
    æĢ§çĹħ
    -0.07
    äsch
    -0.07
    egasus
    -0.07
    诱导
    -0.07
    DESC
    -0.07
    ToFit
    -0.07
    quis
    -0.07
     банкÑĢоÑĤ
    -0.07
    POSITIVE LOGITS
    æĢĿ念
    0.12
    ä¸¤åľ°
    0.11
    缸æĢĿ
    0.10
    -distance
    0.09
    离åĪ«
    0.09
    åĪ«ç¦»
    0.09
     reunion
    0.09
     reun
    0.09
    ä¹ĭæĥħ
    0.09
    éĽ¢
    0.09
    Activations Density 0.052%

    No Known Activations