© 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. 25317
    Prev
    Next
    INDEX
    Explanations

    relationship or state

    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
    örn
    -0.07
    æĺ¯åħ¶
    -0.07
    èģļ
    -0.06
    otron
    -0.06
    arki
    -0.06
     happening
    -0.06
    ÙĴÙĤ
    -0.06
    jÄĻ
    -0.06
     distraction
    -0.06
    ãĤŀ
    -0.06
    POSITIVE LOGITS
    icator
    0.08
    andon
    0.07
    oes
    0.07
    没ä»Ģä¹Ī
    0.07
    Hostname
    0.07
    æĢ§å¥½
    0.07
    unbind
    0.07
     Perg
    0.06
    ban
    0.06
    ording
    0.06
    Activations Density 0.277%

    No Known Activations