© 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. 17398
    Prev
    Next
    INDEX
    Explanations

    php code blocks and functions

    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
    ulg
    -0.06
    alous
    -0.06
     gas
    -0.05
     Na
    -0.05
    ul
    -0.05
     neutral
    -0.05
     na
    -0.05
    éĿ
    -0.05
    Lv
    -0.05
     concentration
    -0.05
    POSITIVE LOGITS
     idei
    0.07
    iked
    0.07
     fray
    0.06
    erano
    0.06
     chec
    0.06
     goofy
    0.06
     TPH
    0.06
     hippoc
    0.06
    estad
    0.06
    ingang
    0.06
    Activations Density 0.056%

    No Known Activations