© 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. 22145
    Prev
    Next
    INDEX
    Explanations

    names in parentheses

    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
    -r
    -0.06
    -s
    -0.05
    паÑĢÑĤа
    -0.05
    æѤæŶçļĦ
    -0.05
    rame
    -0.05
    ativ
    -0.05
    abila
    -0.05
    USA
    -0.05
    åĪĨæŀIJæĬ¥åijĬ
    -0.05
    æĬ¥åijĬ书
    -0.05
    POSITIVE LOGITS
    èĨł
    0.06
    åī¯
    0.06
    親
    0.05
     Elis
    0.05
    esten
    0.05
     diret
    0.05
     Marshal
    0.05
    onders
    0.05
    çĨŁæĤīçļĦ
    0.05
    ocere
    0.05
    Activations Density 0.105%

    No Known Activations