© 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. 22180
    Prev
    Next
    INDEX
    Explanations

    adjective-like, descriptor-noun

    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
    Å¡ti
    -0.06
    æĬ½
    -0.06
    ostra
    -0.06
    istra
    -0.06
    ison
    -0.06
    ordo
    -0.06
    ÑĢÑģкий
    -0.06
    itsu
    -0.06
    IBE
    -0.05
    ilter
    -0.05
    POSITIVE LOGITS
     mre
    0.06
    æĹ¢æľī
    0.05
    multipart
    0.05
    çł´éŨ
    0.05
    è¡ĢèĤī
    0.05
     Evolution
    0.05
    ÃľR
    0.05
    åħįè´¹åľ¨çº¿
    0.05
    urilor
    0.05
     collabor
    0.05
    Activations Density 0.003%

    No Known Activations