© 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. 64236
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
    hsi
    -0.09
    åıªåī©ä¸ĭ
    -0.08
    iphers
    -0.08
    zam
    -0.08
    gems
    -0.08
    skap
    -0.08
    _proba
    -0.08
    nock
    -0.08
    ierungs
    -0.08
    elib
    -0.07
    POSITIVE LOGITS
    æīį对
    0.09
    æīįæĺ¯
    0.08
     rather
    0.08
     later
    0.07
    èĢĮä¸įæĺ¯
    0.07
    æīį被
    0.06
    ä¸İæѤ
    0.06
    èĢĮè¦ģ
    0.06
     preced
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    Activations Density 0.036%

    No Known Activations