© 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. 22189
    Prev
    Next
    INDEX
    Explanations

    NIH grants

    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
     bree
    -0.06
    sche
    -0.06
     revolving
    -0.05
    榨
    -0.05
    komp
    -0.05
    eder
    -0.05
    妥åįı
    -0.05
     revolt
    -0.05
     siblings
    -0.05
    áne
    -0.05
    POSITIVE LOGITS
    å°¼
    0.06
     dota
    0.06
    дей
    0.06
    ей
    0.05
    eer
    0.05
    ãĥĭãĥ¼
    0.05
    ä¸Ģè¨Ģ
    0.05
    моÑĤ
    0.05
    ellow
    0.05
    engu
    0.05
    Activations Density 0.099%

    No Known Activations