© 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. 20084
    Prev
    Next
    INDEX
    Explanations

    risk assessment and taking

    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
    ç²Ĺ
    -0.06
    utan
    -0.05
    .ef
    -0.05
    ulu
    -0.05
    æĪĸ缺
    -0.05
    两çĤ¹
    -0.05
    à¦Łà¦¾
    -0.05
    å¦Ļ
    -0.05
    usan
    -0.05
    é«ĺé¢ij
    -0.05
    POSITIVE LOGITS
    nings
    0.06
    aime
    0.06
    aley
    0.06
    ois
    0.06
    以æĿ¥
    0.06
    澤
    0.05
    约å®ļ
    0.05
    omez
    0.05
    ingend
    0.05
    nement
    0.05
    Activations Density 0.001%

    No Known Activations