© 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. 20070
    Prev
    Next
    INDEX
    Explanations

    came upon

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    vel
    -0.06
    æĿIJæĸĻä¸İ
    -0.06
    reff
    -0.06
     rever
    -0.06
    åľ¨æĦı
    -0.06
     distinguished
    -0.06
    ycl
    -0.06
    вод
    -0.05
    åĨħ容ä¸İ
    -0.05
     theirs
    -0.05
    POSITIVE LOGITS
    keit
    0.06
    宵
    0.05
    çł´çģŃ
    0.05
    ä¸ĩå²ģ
    0.05
    ios
    0.05
     Loi
    0.05
     spur
    0.05
    dale
    0.05
    ä¸īæĽ´
    0.05
    andise
    0.05
    Activations Density 0.001%

    No Known Activations