© 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. 19897
    Prev
    Next
    INDEX
    Explanations

    specific or particular characteristics

    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
     εμÏĢ
    -0.06
    ulle
    -0.06
    çĤ¹ä»Ģä¹Ī
    -0.06
    LOC
    -0.06
    æĿŀ
    -0.05
    umble
    -0.05
    å®ŀä¾ĭ
    -0.05
    åIJĮåŁİ
    -0.05
    obile
    -0.05
    uzzi
    -0.05
    POSITIVE LOGITS
    çī¹å®ļçļĦ
    0.09
    çī¹å®ļ
    0.08
     specific
    0.07
    ä¸Ģå®ļçļĦ
    0.06
     particular
    0.06
     spécifique
    0.06
     specifica
    0.06
    onn
    0.06
    .Doc
    0.05
     certain
    0.05
    Activations Density 0.070%

    No Known Activations