© 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. 15590
    Prev
    Next
    INDEX
    Explanations

    legal citations or formulas

    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
    olia
    -0.07
    ao
    -0.07
     اÙĦÙĪ
    -0.06
    屿
    -0.06
    ะ
    -0.06
    adam
    -0.06
     Jame
    -0.06
    çĻ¾å§ĵç½ij
    -0.06
    apul
    -0.06
    åħ·
    -0.06
    POSITIVE LOGITS
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.08
    ending
    0.08
    å¹ķåIJİ
    0.07
    .newInstance
    0.07
    θαν
    0.07
    äºĨä¸ĢåĪĩ
    0.07
    _RUNTIME
    0.07
    æĬľãģį
    0.07
    yme
    0.07
    clipboard
    0.07
    Activations Density 0.065%

    No Known Activations