© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22607
    Prev
    Next
    INDEX
    Explanations

    `cli.Ui`

    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
    Negative Logits
    ama
    -0.06
    ammo
    -0.05
    pane
    -0.05
    fach
    -0.05
    enton
    -0.05
    apun
    -0.05
    对äºİéĤ£äºĽ
    -0.05
    typed
    -0.05
    Įĵ
    -0.05
    对äºİè¿ĻäºĽ
    -0.05
    POSITIVE LOGITS
    reek
    0.06
    å¾·æĻº
    0.05
    nya
    0.05
    ék
    0.05
    upi
    0.05
     balk
    0.05
     Ñģко
    0.05
    áĥIJáĥ¢
    0.05
    èĻij
    0.05
    åĬłå°Ķ
    0.05
    Activations Density 0.145%

    No Known Activations