© 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. 20126
    Prev
    Next
    INDEX
    Explanations

    euphoria, comfort, sedation, peace, fullness, effects

    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
    lfw
    -0.06
    acar
    -0.06
    agenda
    -0.06
    ç¹ģ
    -0.06
    vene
    -0.05
     Dos
    -0.05
     Catar
    -0.05
    .detect
    -0.05
    è¶Ł
    -0.05
    è¿Ń
    -0.05
    POSITIVE LOGITS
    èĨľ
    0.05
    åĪ¹éĤ£
    0.05
    -beta
    0.05
    ahari
    0.05
     sovereign
    0.05
    شر
    0.05
    ä¸ŃéĹ´çļĦ
    0.05
     ampi
    0.05
    à¹Ģà¸Ĭืà¹Īà¸Ńมัà¹Īà¸Ļ
    0.05
    ãĥĭãĥ¼
    0.05
    Activations Density 0.018%

    No Known Activations