© 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. 27384
    Prev
    Next
    INDEX
    Explanations

    impacts and results

    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
    coni
    -0.09
    arach
    -0.08
    严äºİ
    -0.08
    严峻
    -0.08
    permit
    -0.07
     εÏĢικ
    -0.07
    umpf
    -0.07
     подоз
    -0.07
    Severity
    -0.07
    portun
    -0.07
    POSITIVE LOGITS
    çļĦæķĪæŀľ
    0.13
    æĪIJæķĪ
    0.12
    æķĪæŀľ
    0.12
     outcomes
    0.12
    æķĪæŀľçļĦ
    0.11
     effectiveness
    0.11
    æĪIJæŀľ
    0.11
    è§ģæķĪ
    0.11
     improvements
    0.11
     measurable
    0.11
    Activations Density 0.263%

    No Known Activations