© 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. 59788
    Prev
    Next
    INDEX
    Explanations

    this followed by demonstrative context

    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
    Negative Logits
    ebi
    -0.07
    å¾ħå®ļ
    -0.07
    òi
    -0.07
    ILT
    -0.07
     herein
    -0.07
    club
    -0.07
    uard
    -0.06
    è¿ĻéĩĮæĺ¯
    -0.06
    ecess
    -0.06
    åIJĦå¼ı
    -0.06
    POSITIVE LOGITS
    :
    0.09
    $:
    0.09
    __:
    0.08
    _:
    0.08
    `:
    0.08
    ":
    0.08
    urit
    0.08
    ancen
    0.08
    :")
    0.08
    :`
    0.08
    Activations Density 0.550%

    No Known Activations