© 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. 17955
    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
    enders
    -0.05
    ä¼Ĺ
    -0.05
    zor
    -0.05
    ä¾ĽåºĶ
    -0.05
    IJ
    -0.05
    ç±³
    -0.05
    ieder
    -0.04
    illage
    -0.04
     Neo
    -0.04
    æĻĵ
    -0.04
    POSITIVE LOGITS
    æľĿ天
    0.07
    $j
    0.07
     tue
    0.07
    pä
    0.06
    LG
    0.06
    å®ľ
    0.06
    enate
    0.06
    ä»
    0.06
    iners
    0.06
    EDURE
    0.06
    Activations Density 0.000%

    No Known Activations