© 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. 21492
    Prev
    Next
    INDEX
    Explanations

    theoretical concepts

    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
    _TYP
    -0.09
    liness
    -0.08
    est
    -0.08
    edd
    -0.08
    alha
    -0.08
    jenigen
    -0.08
    estr
    -0.08
    esten
    -0.08
    xiety
    -0.07
    veis
    -0.07
    POSITIVE LOGITS
    oretical
    0.10
    ical
    0.07
    ìłģìľ¼ë¡ľ
    0.07
    ìłģìľ¼ë¡ľëĬĶ
    0.07
    ìłģìĿ¸
    0.07
    åĴĮå®ŀè·µ
    0.07
     unlimited
    0.07
    ity
    0.07
    ually
    0.06
    gorithm
    0.06
    Activations Density 0.011%

    No Known Activations