© 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. 18642
    Prev
    Next
    INDEX
    Explanations

    following keywords

    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
    oop
    -0.07
    ollo
    -0.06
    aret
    -0.06
    adeira
    -0.06
    träg
    -0.06
     ضÙħ
    -0.06
    amentul
    -0.06
    æŃī
    -0.06
    bev
    -0.06
    undle
    -0.06
    POSITIVE LOGITS
    кок
    0.05
    0.05
     deeply
    0.05
    anic
    0.05
    aud
    0.05
     sake
    0.05
     quickly
    0.05
    –
    0.05
     råd
    0.05
    åĵĩ
    0.05
    Activations Density 0.001%

    No Known Activations