© 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. 19149
    Prev
    Next
    INDEX
    Explanations

    massage and physical therapy

    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
    LAM
    -0.06
    etal
    -0.06
    an
    -0.06
    ets
    -0.06
    aS
    -0.06
    nings
    -0.06
    akistan
    -0.06
    ectu
    -0.06
    etes
    -0.06
    hardt
    -0.06
    POSITIVE LOGITS
    antik
    0.06
    æľīåĬŁ
    0.06
    æľīç¦ı
    0.05
    бÑĥдÑĮÑĤе
    0.05
    ez
    0.05
     root
    0.05
    ive
    0.05
    æ·±å±Ĥ次
    0.05
    ÑĥÑħ
    0.05
     rom
    0.05
    Activations Density 0.001%

    No Known Activations