© 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. 20971
    Prev
    Next
    INDEX
    Explanations

    creating elements or objects

    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
     Dep
    -0.06
    aru
    -0.06
    aray
    -0.06
    ierz
    -0.06
    ĵ¨
    -0.05
    ¢
    -0.05
    atge
    -0.05
    apore
    -0.05
    raph
    -0.05
    è¿ľå¤§
    -0.05
    POSITIVE LOGITS
     pros
    0.06
    éĻħ
    0.06
    æĸ°åĬłåĿ¡
    0.05
    è¾¾
    0.05
    aks
    0.05
     âĢ¦
    0.05
    伺
    0.05
    åİĨ
    0.05
    åĦ¿
    0.05
    alis
    0.05
    Activations Density 0.001%

    No Known Activations