© 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. 19208
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ä¹į
    -0.05
    èĩ³å°ij
    -0.05
    igin
    -0.05
    uten
    -0.05
    åıĤçħ§
    -0.05
    atur
    -0.05
     fre
    -0.05
    stur
    -0.05
    e
    -0.05
    âr
    -0.05
    POSITIVE LOGITS
    éĢļè¿ĩ使çĶ¨
    0.06
    Americ
    0.06
    à§įয
    0.05
     paru
    0.05
     íĨµíķľ
    0.05
    ommel
    0.05
    anni
    0.05
    å°±çĶ±
    0.05
    æĥħçIJĨ
    0.05
    ابÙĤ
    0.05
    Activations Density 0.042%

    No Known Activations