© 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. 24954
    Prev
    Next
    INDEX
    Explanations

    video path identifiers

    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
    ä½Ļåħī
    -0.07
    åħ¨æľ¬å°ı说
    -0.06
    antlr
    -0.06
     (~(
    -0.06
    _pull
    -0.06
    ª
    -0.06
    (priority
    -0.06
    à¬ħ
    -0.06
    åħīçݯ
    -0.06
    Apis
    -0.06
    POSITIVE LOGITS
    éī´
    0.07
    å±±å·Ŀ
    0.07
     ::=
    0.07
    Ñģами
    0.07
    å¸Īéķ¿
    0.07
    nz
    0.07
    çĶ¨ä»Ģä¹Ī
    0.07
    nx
    0.06
    auh
    0.06
    ajer
    0.06
    Activations Density 0.011%

    No Known Activations