© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18709
    Prev
    Next
    INDEX
    Explanations

    class/function/variable declarations

    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
    Ignore
    -0.06
    å¼ķæĿ¥
    -0.06
    iga
    -0.06
    ivit
    -0.05
    EEE
    -0.05
    çĶŁäºĨ
    -0.05
    æľīä½Ļ
    -0.05
    Log
    -0.05
    onga
    -0.05
    å¥ĸæĥ©
    -0.05
    POSITIVE LOGITS
     sekret
    0.06
    amples
    0.06
    ç²±
    0.05
    æĹ¥åħ¬å¸ĥ
    0.05
    η
    0.05
    adow
    0.05
    gian
    0.05
    åij½é¢ĺ
    0.05
    .Key
    0.05
    raad
    0.05
    Activations Density 0.014%

    No Known Activations