© 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. 64413
    Prev
    Next
    INDEX
    Explanations

    (List Savings Account

    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
    ayed
    -0.07
    ä¸Ģ缮
    -0.07
    ä¸įè¦ģ
    -0.06
    åı¯æ¢¦
    -0.06
    æ¡ĥèĬ±
    -0.06
    å¨ħ
    -0.06
    ogn
    -0.06
    å°ıæ¡¥
    -0.06
    callable
    -0.06
    AY
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩ以ä¸Ĭ
    0.09
    æĪij们ä¼ļåľ¨
    0.08
    çļĦè¿Ļä¸Ģ
    0.08
    çļĦè¿Ļç§į
    0.08
    -chevron
    0.07
    å½Ĵæł¹
    0.07
    åħħåĪĨåľ°
    0.07
    odem
    0.07
    Äĥm
    0.07
    Mahon
    0.07
    Activations Density 0.004%

    No Known Activations