© 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. 17030
    Prev
    Next
    INDEX
    Explanations

    details required

    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
    æĸ¹
    -0.05
    '
    -0.05
    åįĥåŃĹ
    -0.05
    çĦ¦
    -0.05
    ity
    -0.05
    tec
    -0.05
     col
    -0.05
     paes
    -0.05
     o
    -0.04
    è¯Ĩ
    -0.04
    POSITIVE LOGITS
    lade
    0.07
    é«ĺèĽĭçĻ½
    0.07
    arif
    0.06
     **.**
    0.06
    ernt
    0.06
    leine
    0.06
    êle
    0.06
    ommel
    0.06
    æĻ®éĢļä¼ļåijĺ
    0.06
    ertino
    0.06
    Activations Density 0.001%

    No Known Activations