© 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. 18204
    Prev
    Next
    INDEX
    Explanations

    glow, neon, fluorescence

    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
    ÙĦاÙĦ
    -0.08
    brains
    -0.07
    å¢ŀæķĪ
    -0.07
    æľºæ¢°åĮĸ
    -0.07
    luš
    -0.07
    esistenza
    -0.07
    ÑģÑĤоиÑĤ
    -0.07
    azzi
    -0.06
    waves
    -0.06
    epad
    -0.06
    POSITIVE LOGITS
    ity
    0.05
    èque
    0.05
    身æķĻ
    0.05
     breath
    0.04
    atch
    0.04
    æħ°
    0.04
    ting
    0.04
    vis
    0.04
    heart
    0.04
    Heart
    0.04
    Activations Density 0.003%

    No Known Activations