© 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. 55965
    Prev
    Next
    INDEX
    Explanations

    negligible or insignificant values

    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
    umpang
    -0.07
    warts
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    eck
    -0.07
    çī¹å®ļçļĦ
    -0.07
    ient
    -0.06
    eturn
    -0.06
    lbrace
    -0.06
    ehn
    -0.06
     turn
    -0.06
    POSITIVE LOGITS
     negligible
    0.16
    å¾®ä¸į足
    0.13
     insignificant
    0.12
    å¾®ä¸į足éģĵ
    0.11
     neglig
    0.10
    忽çķ¥
    0.10
    次è¦ģ
    0.10
     ignored
    0.10
     neglected
    0.10
     irrelevant
    0.09
    Activations Density 0.015%

    No Known Activations