© 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. 20866
    Prev
    Next
    INDEX
    Explanations

    formatting placeholders e.g. %s

    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
    wa
    -0.06
    Default
    -0.06
     default
    -0.05
    DEFAULT
    -0.05
     broadcast
    -0.05
     Default
    -0.05
    default
    -0.05
     оÑĤно
    -0.05
    es
    -0.05
     amat
    -0.05
    POSITIVE LOGITS
    å·®
    0.07
    以ä¸ĭæŃ¥éª¤
    0.06
    ogr
    0.06
    以ä¸ĭãģ®
    0.06
    èİ·å¾ĹæĪIJåĬŁ
    0.05
    å·®çļĦ
    0.05
    acent
    0.05
     mobi
    0.05
    以ä¸ĭåĨħ容
    0.05
    obl
    0.05
    Activations Density 0.003%

    No Known Activations