© 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. 20164
    Prev
    Next
    INDEX
    Explanations

    emotions and reactions

    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
     v
    -0.05
     Bir
    -0.05
     bir
    -0.05
    ai
    -0.05
    ri
    -0.05
    oe
    -0.05
    çĵ
    -0.04
    äºĪ
    -0.04
    ir
    -0.04
    æĴŀ
    -0.04
    POSITIVE LOGITS
    ingat
    0.08
    eltas
    0.07
    æ¡Įä¸Ĭ
    0.07
    oubted
    0.07
    级以ä¸Ĭ
    0.06
    truct
    0.06
    entiful
    0.06
    èches
    0.06
    efs
    0.06
    dings
    0.06
    Activations Density 0.003%

    No Known Activations