© 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. 18498
    Prev
    Next
    INDEX
    Explanations

    Adam designed us from Health

    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
    ing
    -0.06
     epit
    -0.05
     often
    -0.05
    orage
    -0.05
    åĽ½æĥħ
    -0.05
     liitt
    -0.05
    常常
    -0.05
    èµ·
    -0.05
    åħ¥éĩij
    -0.05
    éĽª
    -0.05
    POSITIVE LOGITS
    anic
    0.07
    ziale
    0.06
    æѤåīįçļĦ
    0.06
    achts
    0.06
    Hung
    0.06
    oves
    0.06
    amen
    0.06
    ënd
    0.05
    ello
    0.05
    hardt
    0.05
    Activations Density 0.005%

    No Known Activations