© 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. 18766
    Prev
    Next
    INDEX
    Explanations

    greetings

    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
    r
    -0.06
     ch
    -0.05
     m
    -0.05
     w
    -0.05
     h
    -0.05
    m
    -0.05
     s
    -0.05
     imp
    -0.05
    ns
    -0.05
     n
    -0.05
    POSITIVE LOGITS
     disert
    0.07
    -under
    0.07
    etton
    0.07
    höhe
    0.07
    instanc
    0.07
     saura
    0.07
     seksi
    0.06
    ständen
    0.06
     Escr
    0.06
    hell
    0.06
    Activations Density 0.003%

    No Known Activations