© 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. 17743
    Prev
    Next
    INDEX
    Explanations

    xml or code structures

    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
    us
    -0.06
     fav
    -0.06
     dov
    -0.06
    IV
    -0.06
    دد
    -0.05
     пл
    -0.05
    bu
    -0.05
     lu
    -0.05
    åľ¨åį³
    -0.05
    ono
    -0.05
    POSITIVE LOGITS
    å¾Īä¸į
    0.07
     Señor
    0.06
     Ah
    0.06
    neh
    0.06
    سد
    0.06
    ATCH
    0.06
    kering
    0.06
    çĿĽ
    0.06
    илÑĮ
    0.05
    @c
    0.05
    Activations Density 0.110%

    No Known Activations