© 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. 17395
    Prev
    Next
    INDEX
    Explanations

    technical terms or specific entities

    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
    åĴĮåŁ¹åħ»
    -0.06
    ic
    -0.06
    åIJ¦
    -0.06
    person
    -0.05
     wer
    -0.05
    pec
    -0.05
    zin
    -0.05
    std
    -0.05
    æ¯ıé¢ĺ
    -0.05
    æĦıä¹īä¸Ĭ
    -0.05
    POSITIVE LOGITS
    æĭīåħĭ
    0.06
    æĹłè¸ª
    0.06
     Tone
    0.05
    CLU
    0.05
    alaupun
    0.05
    tvr
    0.05
     Klopp
    0.05
    igli
    0.05
    inez
    0.05
    idenza
    0.05
    Activations Density 0.027%

    No Known Activations