© 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. 51282
    Prev
    Next
    INDEX
    Explanations

    EnvProvider

    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
    gern
    -0.07
    çal
    -0.06
    añas
    -0.06
    oczy
    -0.06
     tän
    -0.06
    éĶĤ离åŃIJ
    -0.06
    ij
    -0.06
    è¶Ł
    -0.06
    anker
    -0.06
    avel
    -0.06
    POSITIVE LOGITS
    اÙĨس
    0.08
    çĦ¶
    0.08
    ç½ķ
    0.07
    被æĪij
    0.07
    çĦ¶å¤§
    0.07
    tery
    0.07
    emek
    0.07
    被她
    0.07
    ç»°
    0.07
     dara
    0.07
    Activations Density 0.001%

    No Known Activations