© 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. 20234
    Prev
    Next
    INDEX
    Explanations

    centrifugal

    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
    wap
    -0.05
    à¹Ģà¸Īาะ
    -0.05
    ecke
    -0.05
    onor
    -0.05
    æĥł
    -0.05
    Neighbor
    -0.05
    åĸľè¿İ
    -0.05
    GROUND
    -0.05
     slate
    -0.04
    漫
    -0.04
    POSITIVE LOGITS
    usto
    0.07
    osl
    0.07
    stal
    0.06
    æĭ¼æIJı
    0.06
    ç§ij
    0.06
     centrif
    0.06
    ÙĪÙĩ
    0.06
    çĶ©
    0.06
     ÙĩÙĪÙĦ
    0.06
    离å¿ĥæľº
    0.06
    Activations Density 0.029%

    No Known Activations