© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18273
    Prev
    Next
    INDEX
    Explanations

    **Objects that are or can be held**

    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
    ripe
    -0.06
    /display
    -0.06
    wit
    -0.05
     Giac
    -0.05
    room
    -0.05
    æīĭ
    -0.05
    +offset
    -0.05
    ewith
    -0.05
    azit
    -0.05
    èĦ±æ°´
    -0.05
    POSITIVE LOGITS
    综åIJĪåĪĨæŀIJ
    0.06
     Reduced
    0.06
    ÙĨدÙĩ
    0.06
    ilde
    0.05
     Clearly
    0.05
     ad
    0.05
    Äĩen
    0.05
    漫
    0.05
    åĪ¶åº¦å»ºè®¾
    0.05
    ãģªãĤĬ
    0.05
    Activations Density 0.008%

    No Known Activations