© 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. 20853
    Prev
    Next
    INDEX
    Explanations

    filed Aug

    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
    icha
    -0.08
    obil
    -0.07
    èĩ³å°ij
    -0.06
    нове
    -0.06
     dynamic
    -0.06
    çĨŁèĥ½
    -0.06
    efe
    -0.06
    stal
    -0.06
    ich
    -0.06
    ức
    -0.06
    POSITIVE LOGITS
    attached
    0.05
    ahn
    0.05
     attached
    0.05
    irth
    0.05
    åħ¨å±Ģ
    0.05
    å¸ĥçļĦ
    0.05
    quit
    0.05
     Fork
    0.05
     input
    0.05
    orbit
    0.05
    Activations Density 0.002%

    No Known Activations