© 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. 49222
    Prev
    Next
    INDEX
    Explanations

    bats, dolphins, caves

    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
     Petty
    -0.07
    adhan
    -0.06
     gam
    -0.06
     grain
    -0.06
    æĻ®æ£®
    -0.06
     nhặt
    -0.06
    à¹Ģมà¹ĩà¸Ķ
    -0.06
    quera
    -0.06
    æ´ĭ
    -0.06
    éĺ²çº¿
    -0.06
    POSITIVE LOGITS
    èĿł
    0.11
    èĿĻèĿł
    0.10
     cave
    0.10
    æ´ŀéĩĮ
    0.09
     caves
    0.09
     Cave
    0.09
    пиÑĤа
    0.08
    æ´ŀ
    0.08
     ausgest
    0.08
    aida
    0.08
    Activations Density 0.039%

    No Known Activations