© 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. 17076
    Prev
    Next
    INDEX
    Explanations

    seasonal change and festivals

    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
    laut
    -0.06
     nue
    -0.06
     Muit
    -0.06
     Brot
    -0.06
    kep
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
     célib
    -0.06
    aney
    -0.06
    fli
    -0.06
    å¤©æľº
    -0.06
    POSITIVE LOGITS
    èĩ£
    0.06
    ient
    0.05
     chy
    0.05
    æŶåĪ»
    0.05
    çł
    0.05
    大åħ¸
    0.05
    å±Ī
    0.05
     pros
    0.05
    ä¾į
    0.05
    á»ī
    0.05
    Activations Density 0.005%

    No Known Activations