© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 866
    Prev
    Next
    INDEX
    Explanations

    detailed analysis, description, or overview

    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
    /her
    -0.09
    飶åįİ
    -0.09
    ality
    -0.09
    èī¯èį¯
    -0.08
    ä¸Ģåı¶
    -0.08
    ambi
    -0.08
    大åħ¸
    -0.08
    UnderTest
    -0.08
    ationally
    -0.08
    ettings
    -0.08
    POSITIVE LOGITS
    ented
    0.08
     enough
    0.07
    l
    0.07
     (>
    0.07
    ç»Ĩèĩ´çļĦ
    0.07
    åħ¥å¾®
    0.07
    zza
    0.07
    详ç»ĨçļĦ
    0.07
    atamente
    0.07
    ly
    0.07
    Activations Density 0.027%

    No Known Activations