© 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. 65370
    Prev
    Next
    INDEX
    Explanations

    explanatory variables and predictors

    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
    efault
    -0.07
    imits
    -0.07
    stile
    -0.07
    è°ģ家
    -0.07
    atto
    -0.07
    è¯ŀçĶŁçļĦ
    -0.07
    éĢłè¯£
    -0.07
     поко
    -0.07
    hiri
    -0.07
    .apps
    -0.07
    POSITIVE LOGITS
     predictors
    0.10
     cov
    0.09
    åıĺéĩıçļĦ
    0.09
     explanatory
    0.09
    åįı
    0.08
    åĪĹ
    0.08
     correlated
    0.08
     predictor
    0.08
     variables
    0.08
    åıĺéĩı
    0.08
    Activations Density 0.088%

    No Known Activations