© 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. 21029
    Prev
    Next
    INDEX
    Explanations

    something

    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
    éĥİ
    -0.06
    æľĹ
    -0.06
    ri
    -0.05
    atic
    -0.05
    交åĬŀ
    -0.05
    ñana
    -0.05
    ала
    -0.05
    æķħäºĭ
    -0.05
    al
    -0.05
    åıī
    -0.05
    POSITIVE LOGITS
    楷
    0.06
    cef
    0.06
    jour
    0.06
    elop
    0.05
    orado
    0.05
    )./
    0.05
    DED
    0.05
    çĶŁäº§è¿ĩç¨ĭ
    0.05
    que
    0.05
    è¿ĩç¨ĭåĴĮ
    0.05
    Activations Density 0.009%

    No Known Activations