© 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. 17769
    Prev
    Next
    INDEX
    Explanations

    last or final occurrences

    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
    éĥ¨åĴĮ
    -0.06
    éĸĢ
    -0.05
    igo
    -0.05
    è´
    -0.05
    çļĵ
    -0.05
    nip
    -0.05
    ä¸įä¸ĭæĿ¥
    -0.05
    å¥ĩ
    -0.05
    éŨ
    -0.05
     imap
    -0.05
    POSITIVE LOGITS
    使çĶ¨åīį
    0.06
    anned
    0.06
    å°ĨæĿ¥
    0.06
    å®¡æł¸åIJİ
    0.06
    ovah
    0.06
     usable
    0.06
    使çĶ¨
    0.06
    Characteristic
    0.05
    ÏħÏĥ
    0.05
    пам
    0.05
    Activations Density 0.033%

    No Known Activations