© 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. 19153
    Prev
    Next
    INDEX
    Explanations

    pro- prefix

    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
    agl
    -0.06
    ове
    -0.06
    ллÑı
    -0.06
    ayani
    -0.06
    -memory
    -0.06
    yanto
    -0.06
    aan
    -0.06
    ãĤīãģĦ
    -0.06
    tics
    -0.06
    è§ģå¾Ĺ
    -0.06
    POSITIVE LOGITS
    æľª
    0.09
    æĪĸæľª
    0.07
    å°ļæľª
    0.07
    /raw
    0.07
    çĬ¶æĢģ
    0.07
    åİŁå§ĭ
    0.06
     raw
    0.06
    æľªå®ĮæĪIJ
    0.06
     Raw
    0.06
    è¿ĺæľª
    0.06
    Activations Density 0.132%

    No Known Activations