© 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. 18305
    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
    åĿı
    -0.05
    auh
    -0.05
    ä»Ģä¹Ī
    -0.05
     Fraser
    -0.05
    è¯ĿéŁ³
    -0.05
    credential
    -0.05
    master
    -0.05
    comb
    -0.05
    antin
    -0.05
    aliases
    -0.05
    POSITIVE LOGITS
    _most
    0.07
    umont
    0.06
    è·Łå¤§å®¶
    0.06
    俱ä¹IJéĥ¨
    0.06
    äºijéľĦ
    0.06
     most
    0.06
    æ°ijæĶ¿éĥ¨
    0.06
    æĪij们ä¸İ
    0.06
    reta
    0.06
    æĹħ游å±Ģ
    0.06
    Activations Density 0.000%

    No Known Activations