© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42326
    Prev
    Next
    INDEX
    Explanations

    indicates necessity or purpose

    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
    _typeof
    -0.07
    zeni
    -0.07
    Untitled
    -0.07
    angk
    -0.07
    /perl
    -0.07
    çĥŃè¯į
    -0.07
     pauta
    -0.07
    å·¥ä½ľæĪĸ
    -0.07
    erven
    -0.07
     "\(
    -0.07
    POSITIVE LOGITS
     seper
    0.07
    ä¼łåħ¥
    0.07
     fucking
    0.07
     -->
    0.07
    åıĤ
    0.07
    çī¹
    0.07
    仿
    0.06
    污æŁĵ
    0.06
    otation
    0.06
    -->
    0.06
    Activations Density 0.780%

    No Known Activations