© 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. 19988
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    gate
    -0.06
    Bulk
    -0.06
    ÙĪد
    -0.05
    ach
    -0.05
     bulk
    -0.05
    ACH
    -0.05
     batch
    -0.05
    curring
    -0.05
    æī¹éĩı
    -0.05
    schein
    -0.05
    POSITIVE LOGITS
    trup
    0.07
    oret
    0.06
    istic
    0.06
    彦
    0.06
    ivat
    0.06
    پرداز
    0.05
    åİ®
    0.05
    ׼׾
    0.05
    èįīåĿª
    0.05
    åĬ¿
    0.05
    Activations Density 0.000%

    No Known Activations