© 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. 20969
    Prev
    Next
    INDEX
    Explanations

    method for doing something

    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
     kino
    -0.06
    ç¤İ
    -0.06
    ục
    -0.06
    EDO
    -0.06
    imitive
    -0.06
    جÙĪ
    -0.06
    èĥ¤
    -0.06
    ỤC
    -0.06
    iciency
    -0.06
     hoof
    -0.06
    POSITIVE LOGITS
    Appro
    0.05
    landet
    0.05
    ture
    0.05
    appro
    0.05
    itm
    0.05
    å¿«æĿ¥
    0.05
    æį¢æĿ¥
    0.05
    tron
    0.05
    reten
    0.05
    æļĤæŶ
    0.05
    Activations Density 0.180%

    No Known Activations