© 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. 18934
    Prev
    Next
    INDEX
    Explanations

    effects of

    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
    null
    -0.06
    ek
    -0.06
    礼
    -0.05
    ÃŃcula
    -0.05
    è°ĥæķ´åĴĮ
    -0.05
    pm
    -0.05
     samen
    -0.05
     decisions
    -0.05
     reorder
    -0.05
    带æĿ¥
    -0.05
    POSITIVE LOGITS
    æ¼ĵ
    0.06
    ncy
    0.06
     vari
    0.06
    ksi
    0.06
    ãĥ©ãĤ¤
    0.06
    лив
    0.05
    çĮĽçĥĪ
    0.05
    ktes
    0.05
    ovol
    0.05
    Minus
    0.05
    Activations Density 0.034%

    No Known Activations