© 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. 21638
    Prev
    Next
    INDEX
    Explanations

    2-in-1, convertible, folding, collapsible

    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
    idd
    -0.06
    etas
    -0.06
    icking
    -0.06
    wald
    -0.06
    antal
    -0.06
    igg
    -0.06
    íĮħ
    -0.06
    ÅĤek
    -0.06
    .imp
    -0.06
    urity
    -0.05
    POSITIVE LOGITS
    åıĺ身
    0.06
    两çĶ¨
    0.06
    hub
    0.06
    åŃĺ
    0.06
    转æį¢
    0.05
    Fold
    0.05
    åĪĩæį¢
    0.05
     convertible
    0.05
    Utility
    0.05
    åķĨä¸ļçĶ¨éĢĶ
    0.05
    Activations Density 0.092%

    No Known Activations