© 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. 20922
    Prev
    Next
    INDEX
    Explanations

    treatments for conditions

    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
     verant
    -0.06
    ässe
    -0.06
    unci
    -0.06
    å°ı説
    -0.06
    .asc
    -0.06
    à¹ģลà¸ģ
    -0.06
    åIJĪ秣
    -0.06
    举足
    -0.05
    eneg
    -0.05
    åĻ©
    -0.05
    POSITIVE LOGITS
    æŁĶ
    0.06
    blem
    0.05
    ided
    0.05
     healing
    0.05
    BS
    0.05
    erial
    0.05
    خر
    0.05
    guided
    0.05
    åĢŁåĬ©
    0.05
    roup
    0.05
    Activations Density 0.049%

    No Known Activations