© 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. 17705
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude or strong consideration

    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
     comfort
    -0.06
    ä¹Łä¸įä¸Ģå®ļ
    -0.05
    okes
    -0.05
    ometimes
    -0.05
     Comfort
    -0.05
    alang
    -0.05
    ort
    -0.05
    çĻ½
    -0.05
    çīµ
    -0.05
    Comfort
    -0.05
    POSITIVE LOGITS
    á»ijng
    0.06
    posa
    0.06
    ammad
    0.06
     popr
    0.06
    hip
    0.06
    suspend
    0.06
    å¿ħä¸įåı¯
    0.05
    usif
    0.05
    ity
    0.05
    hluk
    0.05
    Activations Density 0.002%

    No Known Activations