© 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. 64023
    Prev
    Next
    INDEX
    Explanations

    code identifiers and URLs

    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
    ä¸į离
    -0.07
    _DYNAMIC
    -0.07
    mani
    -0.07
    Įĵ
    -0.07
    ergie
    -0.07
    antium
    -0.06
    å§ĭ
    -0.06
    çĴĢ
    -0.06
     l
    -0.06
    å¤ĸçķĮçļĦ
    -0.06
    POSITIVE LOGITS
    çĶ£
    0.07
    ï¸İ
    0.07
     deserved
    0.07
    åĬªåĬĽæĬĬ
    0.07
    åĴĮ大家åĪĨ享
    0.07
    atora
    0.07
     Ents
    0.07
    lys
    0.07
    ÑĥÑħ
    0.07
    ä¸Ĭ大
    0.07
    Activations Density 0.009%

    No Known Activations