© 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. 18220
    Prev
    Next
    INDEX
    Explanations

    phase, wind, acceleration

    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
    .INSTANCE
    -0.06
    çĿĢ
    -0.06
    èľľæľĪ
    -0.06
    çĿĢå°ı
    -0.05
     initially
    -0.05
     Firstly
    -0.05
     Insomma
    -0.05
    andbox
    -0.05
    ä¸Ģéĸĭå§ĭ
    -0.05
     directly
    -0.05
    POSITIVE LOGITS
     Dét
    0.06
    æİĥ
    0.06
    æī«
    0.06
    ast
    0.06
     afterwards
    0.06
    lect
    0.06
    ارÙĩ
    0.05
    icule
    0.05
    éĶĦ
    0.05
    rote
    0.05
    Activations Density 0.006%

    No Known Activations