© 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. 18375
    Prev
    Next
    INDEX
    Explanations

    list items or enumeration

    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
    æĽ´å¤ļåħ³äºİ
    -0.07
    ombre
    -0.06
     Ih
    -0.06
    ÙĨØ©
    -0.06
    uhu
    -0.06
     thon
    -0.06
     gand
    -0.06
    çļĦè¡Įä¸ļ
    -0.06
    ãģ®ãģ¨ãģĵãĤį
    -0.06
    ensch
    -0.06
    POSITIVE LOGITS
    å·¥ä½ľå¼Ģå±ķ
    0.05
    èľĺèĽĽ
    0.05
    æľĽ
    0.05
     ext
    0.05
    หมà¸Ķ
    0.05
    å§ij
    0.05
    å¼·
    0.05
    æIJŃéħįä¸Ĭ
    0.04
     kennenlernen
    0.04
    没æľī被
    0.04
    Activations Density 0.005%

    No Known Activations