© 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. 21741
    Prev
    Next
    INDEX
    Explanations

    renewal and beginnings

    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
    æģ¬
    -0.06
    è§
    -0.06
    zijd
    -0.06
    ugged
    -0.06
    accumulator
    -0.06
    ÑģÑĮого
    -0.05
     podr
    -0.05
     houd
    -0.05
    æĶ¶èµ·
    -0.05
    笳
    -0.05
    POSITIVE LOGITS
    èľķåıĺ
    0.06
     ger
    0.06
     new
    0.06
    强çĥĪ
    0.06
    åѵåĮĸ
    0.06
     bir
    0.05
    çĶŁçģµ
    0.05
    ÑģÑĤеÑģÑĤвенно
    0.05
     stronger
    0.05
    éĩįçĶŁ
    0.05
    Activations Density 0.013%

    No Known Activations