© 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. 19004
    Prev
    Next
    INDEX
    Explanations

    amazed, shocked, surprised

    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
    à¸Ĺาà¸ĩà¸ģาร
    -0.07
    gether
    -0.07
    ÒĵÑĭ
    -0.07
    каз
    -0.06
    esser
    -0.06
    portun
    -0.06
    zun
    -0.06
    posing
    -0.06
    esity
    -0.06
    /errors
    -0.06
    POSITIVE LOGITS
    äºĨ
    0.05
    -rounded
    0.05
     of
    0.05
    åľ¨è¿ij
    0.05
     rel
    0.05
    s
    0.05
    ยุà¸Ħ
    0.05
    ricks
    0.05
    -chair
    0.04
    åĻ¨çļĦ
    0.04
    Activations Density 0.005%

    No Known Activations