© 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. 18315
    Prev
    Next
    INDEX
    Explanations

    resources in addition to expertise

    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
    rips
    -0.08
     [...]
    -0.08
     Shelter
    -0.07
    ãģ®åīį
    -0.07
    æŶèĩ³
    -0.07
     ..."
    -0.07
     diput
    -0.07
    udas
    -0.07
    opus
    -0.07
    à¸Ĭล
    -0.07
    POSITIVE LOGITS
    بع
    0.07
    人身
    0.07
    çĴŀ
    0.06
     mata
    0.06
    æķ´
    0.06
    _SPECIAL
    0.06
     mani
    0.06
    ç°¿
    0.06
    esto
    0.06
    å·´å°Ķ
    0.06
    Activations Density 0.011%

    No Known Activations