© 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. 17825
    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
    aria
    -0.06
    rien
    -0.06
    orsk
    -0.06
    èµĸ
    -0.05
    arias
    -0.05
    ata
    -0.05
    åıĶ
    -0.05
    ori
    -0.05
    æľºåħ³
    -0.05
    aa
    -0.05
    POSITIVE LOGITS
    ắt
    0.06
    ä¸į顺
    0.06
    -ups
    0.06
     slan
    0.06
     soud
    0.05
    åŃ¦ä¹łåĨħ容
    0.05
    ä¸Ĭé£İ
    0.05
    æ£ĢæŁ¥å·¥ä½ľ
    0.05
    isons
    0.05
    çĥŃçĤ¹éĹ®é¢ĺ
    0.05
    Activations Density 0.000%

    No Known Activations