© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    ‘ Ascending to Berlin

    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
    ä¸įåİĮ
    -0.08
    å¯¹æľ¬æ¬¡
    -0.07
    pty
    -0.07
    Ø«ÙĪر
    -0.07
    èĻij
    -0.07
    çĦ¶åIJİæł¹æį®
    -0.07
    çĶ¸çĶ¸
    -0.07
    irão
    -0.07
    kwargs
    -0.07
    mts
    -0.07
    POSITIVE LOGITS
    cel
    0.08
    zah
    0.07
    çļĦåķĬ
    0.07
    éĽħ
    0.07
    æ¿
    0.06
    theless
    0.06
    صÙĦØŃØ©
    0.06
    ingkan
    0.06
    à¹Ħà¸Ķà¹īà¹Ģลย
    0.06
    oud
    0.06
    Activations Density 0.002%

    No Known Activations