© 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. 18657
    Prev
    Next
    INDEX
    Explanations

    synthetic methods and materials

    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
    ed
    -0.06
    ing
    -0.06
    à¸ģรรม
    -0.05
    i
    -0.05
    icu
    -0.05
    @m
    -0.05
     gỡ
    -0.05
    imis
    -0.05
    æĦŁåĴĮ
    -0.05
    isson
    -0.05
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.08
     dessus
    0.06
    erten
    0.06
    çĤ¹åĩ»æŁ¥çľĭ
    0.06
     stanu
    0.06
    çķĻ念
    0.06
    cke
    0.06
    cking
    0.06
    ormsg
    0.06
    ëĭ¤ëĬĶ
    0.06
    Activations Density 0.002%

    No Known Activations