© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    SQL WHERE clause

    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
    ä¸ĢåĽŀäºĭ
    -0.07
    次äºİ
    -0.06
    omma
    -0.06
    ow
    -0.06
    oy
    -0.06
    æł¼çļĦ
    -0.06
     завеÑĢ
    -0.06
    laces
    -0.06
    ä¸ĭä¸Ģ级
    -0.06
    å¹ħ度
    -0.06
    POSITIVE LOGITS
    票
    0.05
    iar
    0.05
    ä¸Ģéģį
    0.05
    exion
    0.05
    伸
    0.05
    à¸Ľà¸£
    0.05
    nÃŃ
    0.05
    ÑĦÑĸ
    0.05
    edm
    0.05
     shed
    0.05
    Activations Density 0.004%

    No Known Activations