© 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. 918
    Prev
    Next
    INDEX
    Explanations

    digital recording and storage

    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
     PEND
    -0.08
    士ãģ®
    -0.07
    umbu
    -0.07
    å¥½å·¥ä½ľ
    -0.07
    edException
    -0.07
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    å¼Ĥ常çļĦ
    -0.07
    UME
    -0.07
    èĦīæIJı
    -0.07
    -même
    -0.07
    POSITIVE LOGITS
     purely
    0.08
    refs
    0.07
    çĶ³
    0.07
    æ¦ķ
    0.07
    rey
    0.07
    çļĦåħ¶ä»ĸ
    0.07
    éĻ¤æѤ
    0.07
    ä»ħéĻIJäºİ
    0.07
    less
    0.06
    vi
    0.06
    Activations Density 0.131%

    No Known Activations