© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    followed by an answer

    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
    对该
    -0.08
    该款
    -0.08
    usher
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    æŃ¤ä¸¾
    -0.07
    unds
    -0.07
    ä¸ļ绩
    -0.07
    ungg
    -0.07
    为éĩį
    -0.07
    èµĭ
    -0.07
    POSITIVE LOGITS
    åĽŀçŃĶ
    0.07
    çļĦåĽŀçŃĶ
    0.07
     mostly
    0.07
    åĮºåĪĨ
    0.07
    æł¹æľ¬ä¸Ĭ
    0.07
     largely
    0.07
    没æľīéĤ£ä¹Ī
    0.07
    å¤ļéĥ¨
    0.07
     answered
    0.07
    å½Ĵæł¹
    0.06
    Activations Density 0.072%

    No Known Activations