© 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. 20623
    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
    prav
    -0.07
    çĦ¶æĺ¯
    -0.07
    çĦ¶å¤§
    -0.06
    éro
    -0.06
    orny
    -0.06
    åĩıä»ĵ
    -0.06
    go
    -0.05
     tough
    -0.05
    æģŃåĸľ
    -0.05
     toughness
    -0.05
    POSITIVE LOGITS
    ovel
    0.05
    çĻĸ
    0.05
    eee
    0.05
    _ARGUMENT
    0.05
    ads
    0.05
     invent
    0.05
    人士
    0.05
    ONG
    0.05
    åŃ£
    0.05
     personalitÃł
    0.05
    Activations Density 0.000%

    No Known Activations