© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18969
    Prev
    Next
    INDEX
    Explanations

    statements

    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
    oj
    -0.06
    неÑĤа
    -0.06
    utus
    -0.06
    æī¾
    -0.05
    çīµ
    -0.05
    èģª
    -0.05
     fores
    -0.05
    æĹ©
    -0.05
    o
    -0.05
    å¼Ģå±Ģ
    -0.05
    POSITIVE LOGITS
    nder
    0.06
    гей
    0.06
    åıĹçļĦ
    0.06
     rant
    0.06
    aider
    0.06
    stående
    0.06
    æīĢåıĹ
    0.06
    åħ¶ä¸ī
    0.06
    zelf
    0.06
    aisons
    0.06
    Activations Density 0.008%

    No Known Activations