© 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. 20165
    Prev
    Next
    INDEX
    Explanations

    helping us perform tasks

    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
    è§Ĥå¯ŁåĪ°
    -0.06
    aires
    -0.05
    çī¢
    -0.05
     observ
    -0.05
    追
    -0.05
    ä¸ĢæĭĽ
    -0.05
     alert
    -0.05
    ographed
    -0.05
    è§Ĥå¯Ł
    -0.05
    rait
    -0.05
    POSITIVE LOGITS
    å·¥ä½ľéľĢè¦ģ
    0.06
     recrut
    0.06
    adet
    0.06
    é³ŀ
    0.06
    usher
    0.06
    好ä¸į
    0.06
    orsa
    0.06
    abal
    0.06
    æĢ¥çĿĢ
    0.06
     дÑı
    0.06
    Activations Density 0.023%

    No Known Activations