© 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. 18963
    Prev
    Next
    INDEX
    Explanations

    feature selection methods

    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
    hofer
    -0.08
    å¡
    -0.08
    ibern
    -0.07
    usy
    -0.07
    ÑĢаÑı
    -0.07
    ola
    -0.07
    anoia
    -0.07
    OPSIS
    -0.07
    ×ķ×ķ
    -0.06
    ikt
    -0.06
    POSITIVE LOGITS
    åĪł
    0.08
    çŃĽéĢī
    0.07
     List
    0.07
    Subset
    0.07
     blacklist
    0.07
    _subset
    0.07
    åīĶéĻ¤
    0.07
    Ỽt
    0.07
    ä¸Ģç»Ħ
    0.07
     list
    0.07
    Activations Density 0.055%

    No Known Activations