© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    contrasting clauses

    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
    翼翼
    -0.09
    oran
    -0.08
    elly
    -0.08
    ebed
    -0.08
    å·įå·į
    -0.08
    Į
    -0.08
    °
    -0.07
     ugyanis
    -0.07
    olino
    -0.07
    evin
    -0.07
    POSITIVE LOGITS
     nevertheless
    0.10
     nonetheless
    0.09
    åħ¶å®ĥçļĦ
    0.08
    åħ¶å®ĥ
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    并ä¸įæĺ¯
    0.07
    è¿ĺèĥ½å¤Ł
    0.07
    shi
    0.07
    åħ¶ä½Ļ
    0.06
    ...
    0.06
    Activations Density 0.391%

    No Known Activations