© 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. 38861
    Prev
    Next
    INDEX
    Explanations

    criterion, decision, or threshold

    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
    upe
    -0.07
    hurst
    -0.07
    å°Ķ夫
    -0.07
    èµ·å±ħ
    -0.07
    amas
    -0.07
    ziali
    -0.07
    ä¾Ľæ±Ĥ
    -0.06
     masters
    -0.06
    æºIJ
    -0.06
    åİķ
    -0.06
    POSITIVE LOGITS
     criterion
    0.10
     Criterion
    0.10
    Criterion
    0.09
    -runner
    0.08
     decision
    0.08
    æĴĴ
    0.07
    åĪ¤å®ļ
    0.07
    çģµæķı
    0.07
     trigger
    0.07
     threshold
    0.07
    Activations Density 0.001%

    No Known Activations