© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22308
    Prev
    Next
    INDEX
    Explanations

    age, year, date, month, time

    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
    è¿·æĥij
    -0.05
     kib
    -0.05
     dil
    -0.05
    send
    -0.05
    egin
    -0.05
     se
    -0.05
    åĩŃåĢŁåħ¶
    -0.05
    bred
    -0.05
    åĪĺæĻĵ
    -0.05
    æĥĬéĨĴ
    -0.05
    POSITIVE LOGITS
    eca
    0.06
    expect
    0.06
    ä¾ĭè¡Į
    0.06
    è¡¡
    0.06
    主è¦ģä»İ
    0.06
    è´¨æķĪ
    0.06
    å¾·æĻº
    0.06
    igit
    0.06
    wsze
    0.06
    æľªå®Į
    0.05
    Activations Density 0.007%

    No Known Activations