© 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. 18595
    Prev
    Next
    INDEX
    Explanations

    caffeine and nicotine elimination

    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
    quo
    -0.06
    ox
    -0.06
    onga
    -0.05
    æºĿ
    -0.05
    éĺŁåľ¨
    -0.05
     mong
    -0.05
    rompt
    -0.05
     moo
    -0.05
    au
    -0.05
    iket
    -0.05
    POSITIVE LOGITS
    wiad
    0.06
    pring
    0.06
    ýt
    0.06
    fluence
    0.06
    ested
    0.05
    gå
    0.05
    ä¿ĿæĮģé«ĺ度
    0.05
    æݧåĪ¶çļĦ
    0.05
     portion
    0.05
    shell
    0.05
    Activations Density 0.004%

    No Known Activations