© 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. 18873
    Prev
    Next
    INDEX
    Explanations

    arithmetic and algebraic expressions

    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
    alama
    -0.06
    çľ¼åīįä¸Ģ亮
    -0.05
    çģ«èħ¿
    -0.05
    иÑģÑĮ
    -0.05
    幸
    -0.05
    пен
    -0.05
    íħĮìĿ¸
    -0.05
     hack
    -0.05
    volve
    -0.05
    /null
    -0.05
    POSITIVE LOGITS
    Ent
    0.05
    zek
    0.05
    ä¸ĢåĪ»
    0.05
    ä¸īéĩĮ
    0.05
    ãĢĮ
    0.05
    arem
    0.05
    å¼ı
    0.05
    ضÙĬØ©
    0.05
    iolet
    0.05
    s
    0.05
    Activations Density 0.003%

    No Known Activations