© 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. 18158
    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
    ä¸Ģç§į
    -0.06
    .shape
    -0.06
    laus
    -0.06
    ill
    -0.05
    æĺİç¡®è¦ģæ±Ĥ
    -0.05
    helm
    -0.05
    avera
    -0.05
    anee
    -0.05
     Null
    -0.05
    dh
    -0.05
    POSITIVE LOGITS
    ecca
    0.07
    åŁĭèij¬
    0.06
    å¾ĹçĽĬ
    0.06
    kening
    0.05
    ลัà¸ĩ
    0.05
    rowning
    0.05
     carefully
    0.05
    chal
    0.05
    room
    0.05
    odate
    0.05
    Activations Density 0.000%

    No Known Activations