© 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. 17176
    Prev
    Next
    INDEX
    Explanations

    paths and executables

    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
    åĽ´
    -0.05
     admir
    -0.05
     crypt
    -0.05
     expansion
    -0.05
    å¢
    -0.05
    åIJ«
    -0.05
    åĬłå¯Ĩ
    -0.05
     audi
    -0.05
    åľį
    -0.05
    1
    -0.04
    POSITIVE LOGITS
     scarce
    0.06
    èĥ½åĬĽçļĦ
    0.06
     Blades
    0.06
    çĽĸä¸Ĭ
    0.06
    è´±
    0.06
    avana
    0.06
    ç¦Ģ
    0.06
    andar
    0.06
    æµĬ
    0.06
    ebilecek
    0.06
    Activations Density 0.048%

    No Known Activations