© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18054
    Prev
    Next
    INDEX
    Explanations

    latest/modern/advanced technology

    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
    ulet
    -0.06
    ÑĨÑİ
    -0.06
    inen
    -0.06
    æ¯ĵ
    -0.05
    åĭĥ
    -0.05
    uropa
    -0.05
    imonial
    -0.05
     Ùħباش
    -0.05
    çĽĺçļĦ
    -0.05
    çĿĢä¸Ģ个
    -0.05
    POSITIVE LOGITS
    ServerError
    0.06
    è·»
    0.06
    hra
    0.06
    udin
    0.06
    ÙĪاÙĤ
    0.06
    etch
    0.06
    åĨħ容æıIJä¾Ľæĸ¹
    0.05
    عاÙĨ
    0.05
    hoff
    0.05
    itional
    0.05
    Activations Density 0.001%

    No Known Activations