© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27060
    Prev
    Next
    INDEX
    Explanations

    past belief or state

    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
    å½ĵåīį
    -0.10
    æĻ®æ®µ
    -0.09
     presently
    -0.08
     currently
    -0.08
    å½ĵåīįçļĦ
    -0.08
    å¹³æŶçļĦ
    -0.08
    缮åīį没æľī
    -0.08
    缮åīį
    -0.08
     derzeit
    -0.08
    currently
    -0.08
    POSITIVE LOGITS
    ä½ĨéļıçĿĢ
    0.15
    å½ĵæŶ
    0.14
    å½ĵæŶçļĦ
    0.14
    éĤ£æŶåĢĻ
    0.14
    éĤ£æŶ
    0.14
    ä½Ĩçİ°åľ¨
    0.14
    éĤ£æŶçļĦ
    0.14
    èĢĮçİ°åľ¨
    0.14
    èĢĮå¦Ĥä»Ĭ
    0.13
    .Now
    0.12
    Activations Density 0.954%

    No Known Activations