© 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. 22110
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    è¶ħ大
    -0.08
    apes
    -0.06
     gigantic
    -0.06
    ingga
    -0.06
     Huge
    -0.06
    人ãĤĤå¤ļãģĦ
    -0.06
    append
    -0.06
    achter
    -0.06
     zade
    -0.06
    Appending
    -0.06
    POSITIVE LOGITS
    å°ı声
    0.06
    åħ¶
    0.05
    å°ıåĮħ
    0.05
    å±ĤéĿ¢
    0.05
     MODE
    0.05
    mena
    0.05
    èı
    0.05
    MODE
    0.05
    slt
    0.05
    ä½İ声
    0.05
    Activations Density 0.239%

    No Known Activations