© 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. 7878
    Prev
    Next
    INDEX
    Explanations

    refraction, drag, vibration, dependence, stresses

    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
    ouce
    -0.08
    以赴
    -0.08
    飶åįİ
    -0.08
    å¿ĥ缮
    -0.08
    нва
    -0.07
    ä¸įåı¯æĢķ
    -0.07
    èѬå¦Ĥ
    -0.07
    .recv
    -0.07
    laub
    -0.07
    è¦ģä¹Ī
    -0.07
    POSITIVE LOGITS
    hu
    0.07
    INST
    0.07
    zt
    0.07
    yu
    0.06
    CTR
    0.06
    inh
    0.06
    çµ®
    0.06
    optim
    0.06
     signalling
    0.06
    親
    0.06
    Activations Density 0.073%

    No Known Activations