© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19238
    Prev
    Next
    INDEX
    Explanations

    variable names or mathematical symbols followed by 'in'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    欺
    -0.06
    çīĩåĪ»
    -0.06
    pg
    -0.05
    rechnung
    -0.05
    filt
    -0.05
    üy
    -0.05
     saf
    -0.05
    truct
    -0.05
    æĵį纵
    -0.05
    culture
    -0.05
    POSITIVE LOGITS
    idot
    0.06
    uran
    0.06
     âĢ¢
    0.06
    aga
    0.05
    umpl
    0.05
    uent
    0.05
    ansa
    0.05
    issons
    0.05
    uce
    0.05
    å°Ķå¤ļ
    0.05
    Activations Density 0.005%

    No Known Activations