© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19331
    Prev
    Next
    INDEX
    Explanations

    metaphorical language

    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
    åĻ¨çŃī
    -0.06
    encias
    -0.06
    icated
    -0.06
    otto
    -0.06
    ÑīеÑģÑĤв
    -0.06
    velopp
    -0.05
    ä¸įèµ·æĿ¥
    -0.05
    æīĢæĥ³
    -0.05
    éģIJ
    -0.05
    inium
    -0.05
    POSITIVE LOGITS
    wel
    0.07
    ish
    0.06
    dür
    0.06
    ãĢħ
    0.06
    aul
    0.06
    ед
    0.06
    aut
    0.06
    称
    0.05
     ÑģмÑĭ
    0.05
    çļĦæĶ¿æ²»
    0.05
    Activations Density 0.003%

    No Known Activations