© 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. 21075
    Prev
    Next
    INDEX
    Explanations

    path manipulation and urls

    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
     skor
    -0.05
    æĪ¿éĹ´åĨħ
    -0.05
     panel
    -0.05
    еÑģÑĤв
    -0.05
     Dak
    -0.05
    agger
    -0.05
    寿
    -0.05
    ÅĤow
    -0.05
     numeros
    -0.05
    åĪ«æĹł
    -0.05
    POSITIVE LOGITS
    endir
    0.06
     Wolfs
    0.06
    mers
    0.06
     Navigation
    0.06
    导èĪª
    0.06
     Navig
    0.05
    .lu
    0.05
     scom
    0.05
    ucid
    0.05
    éĩĮç¨ĭ
    0.05
    Activations Density 0.061%

    No Known Activations