© 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. 18387
    Prev
    Next
    INDEX
    Explanations

    concern about risks

    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
    azit
    -0.06
    mino
    -0.06
    apé
    -0.06
     далÑĮ
    -0.06
    wich
    -0.05
     thôi
    -0.05
    antino
    -0.05
    èĤ¡æĿĥç»ĵæŀĦ
    -0.05
    åĮĸ解
    -0.05
    ги
    -0.05
    POSITIVE LOGITS
     Ø®ÙĦ
    0.05
    èĢģå¸Īåľ¨
    0.05
    _NUMERIC
    0.05
    embra
    0.05
    ืà¹Īà¸Ļ
    0.05
    .utilities
    0.05
     advent
    0.05
    avl
    0.05
    å¨ĵ
    0.05
    -runner
    0.05
    Activations Density 0.018%

    No Known Activations