© 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. 17213
    Prev
    Next
    INDEX
    Explanations

    Portland Press Herald

    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
    è¯·çĽ´æİ¥
    -0.06
    دÙĪÙĨ
    -0.06
    à¹īาà¸ĩ
    -0.05
    æĹłéľĢ
    -0.05
    ple
    -0.05
    udah
    -0.05
    odus
    -0.05
    åįĥåı¤
    -0.05
    æĿĨ
    -0.05
    èĵ¬
    -0.05
    POSITIVE LOGITS
    wann
    0.07
    onica
    0.06
    çī¹æ´¾
    0.06
     ноÑĤ
    0.06
    _top
    0.06
    servername
    0.06
    身çĤº
    0.06
    érons
    0.06
    omma
    0.05
    rocket
    0.05
    Activations Density 0.002%

    No Known Activations