© 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. 17728
    Prev
    Next
    INDEX
    Explanations

    armor, shields, gear

    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
    orch
    -0.06
    ç»ħ士
    -0.06
    geb
    -0.06
    γκα
    -0.06
    izer
    -0.06
    ariat
    -0.06
    gerak
    -0.06
    ÑģпоÑģобноÑģÑĤÑĮ
    -0.05
    eh
    -0.05
     Kurd
    -0.05
    POSITIVE LOGITS
    stal
    0.05
    olk
    0.05
    ves
    0.05
     sarc
    0.05
    ures
    0.05
    åºŀ
    0.05
    zes
    0.05
    å®Įæķ´
    0.05
    ↵     ↵
    0.05
     pes
    0.05
    Activations Density 0.003%

    No Known Activations