© 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. 19287
    Prev
    Next
    INDEX
    Explanations

    attending school or events regularly

    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
    grad
    -0.06
    åŃ©
    -0.06
     finalists
    -0.06
     sooner
    -0.06
    perm
    -0.05
    .goBack
    -0.05
    æĶ¾æīĭ
    -0.05
    ợt
    -0.05
     ÑģоÑģÑĤ
    -0.05
     Cath
    -0.05
    POSITIVE LOGITS
    éĢīæĭ©æĢ§
    0.07
     attendance
    0.06
    缺失
    0.06
     interpol
    0.06
     Attendance
    0.06
     (%)
    0.06
     interpolated
    0.05
    missing
    0.05
     interpolation
    0.05
     selective
    0.05
    Activations Density 0.022%

    No Known Activations