© 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. 44824
    Prev
    Next
    INDEX
    Explanations

    output data structures

    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
     organ
    -0.06
    %C
    -0.06
    LR
    -0.06
    ïs
    -0.06
    çĶļ
    -0.06
    çIJĨæĥ³
    -0.05
    ì§ľ
    -0.05
    å°ģ
    -0.05
    inta
    -0.05
    主ä¹īçļĦ
    -0.05
    POSITIVE LOGITS
    urch
    0.09
    çĸµ
    0.08
    лко
    0.08
    ikin
    0.08
    timezone
    0.07
    讲æĶ¿æ²»
    0.07
    ÑĤÑĢо
    0.07
    äste
    0.07
    å®ĺæĸ¹å¾®ä¿¡
    0.07
    okie
    0.07
    Activations Density 0.003%

    No Known Activations