© 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. 18144
    Prev
    Next
    INDEX
    Explanations

    past decades

    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
    ong
    -0.06
    eries
    -0.05
    r
    -0.05
    å¦Ĥæŀľæ²¡æľī
    -0.05
    te
    -0.05
    vers
    -0.05
    itters
    -0.05
     ti
    -0.05
    untu
    -0.05
    符åIJĪæĿ¡ä»¶çļĦ
    -0.05
    POSITIVE LOGITS
    ared
    0.07
    ekat
    0.07
    -minded
    0.06
    volmente
    0.06
    åĮĸåıijå±ķ
    0.06
    roup
    0.06
     theirs
    0.06
    äºİ人
    0.06
    owns
    0.06
    ä¸Ģå®ļç¨ĭ度
    0.06
    Activations Density 0.021%

    No Known Activations