© 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. 26290
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    avent
    -0.10
    åħĭéļ¾
    -0.09
    omie
    -0.08
    ettel
    -0.08
    太éļ¾
    -0.08
    IBC
    -0.08
    è§Ĩç½ij
    -0.07
    มาà¸ģà¹Ģà¸ģิà¸Ļà¹Ħà¸Ľ
    -0.07
    obi
    -0.07
    inet
    -0.07
    POSITIVE LOGITS
    èĻ½å°ı
    0.14
     nonetheless
    0.10
     nevertheless
    0.09
    ä¸įåı¯å¿½è§Ĩ
    0.09
     enough
    0.08
    ä¸į容忽è§Ĩ
    0.08
    åį´æĺ¯
    0.08
     lumayan
    0.08
    累积
    0.08
    å¦Ĥæ¶īåıĬ
    0.07
    Activations Density 0.285%

    No Known Activations