© 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. 19005
    Prev
    Next
    INDEX
    Explanations

    position and order indicators

    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
    é»
    -0.06
    ells
    -0.05
    éļ
    -0.05
     specific
    -0.05
     intern
    -0.05
    ab
    -0.05
    "
    -0.05
     Specific
    -0.05
     plus
    -0.05
     ar
    -0.05
    POSITIVE LOGITS
    меÑģÑĤи
    0.07
    å®ĥèĥ½å¤Ł
    0.07
    coce
    0.07
    ä¸İåĽ½åĨħ
    0.07
    ingg
    0.07
     conseguido
    0.07
    建设æĪIJ为
    0.07
    ä¸İ客æĪ·
    0.06
    æ°ĶäºĨ
    0.06
    lete
    0.06
    Activations Density 0.072%

    No Known Activations