© 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. 19272
    Prev
    Next
    INDEX
    Explanations

    create git branches

    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±ģ
    -0.05
    FFE
    -0.05
    èĭ¥
    -0.05
    éĢĤ
    -0.05
     it
    -0.05
    å·®
    -0.05
    解
    -0.04
     if
    -0.04
    (
    -0.04
    å®ĥ
    -0.04
    POSITIVE LOGITS
    atcher
    0.06
    åĭĭ
    0.06
    ubern
    0.06
    rael
    0.06
    queo
    0.06
    eminen
    0.06
    راط
    0.06
    ä¸ĭè¾ĸ
    0.06
     tougher
    0.06
     spree
    0.06
    Activations Density 0.011%

    No Known Activations