© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    legal citations and volumes

    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
    abb
    -0.08
    åĶ
    -0.07
    oux
    -0.07
    åĢ
    -0.07
    yd
    -0.07
    ibd
    -0.07
    累累
    -0.07
    ombok
    -0.06
    azol
    -0.06
    og
    -0.06
    POSITIVE LOGITS
    ì°©
    0.07
    åĮºå¸Ĥ
    0.07
     Stra
    0.07
    åĪ°èĢģ
    0.07
    ÙħاÛĮ
    0.07
    енÑĤаÑĨиÑı
    0.07
    Charts
    0.07
    zcze
    0.07
    OLA
    0.07
    irin
    0.07
    Activations Density 0.036%

    No Known Activations