© 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. 17889
    Prev
    Next
    INDEX
    Explanations

    UI element boundaries and layout

    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
    abel
    -0.06
    lal
    -0.06
    ascar
    -0.06
    ä¸ĢæıIJ
    -0.06
    ÄĥtÄĥ
    -0.05
    lash
    -0.05
    ächst
    -0.05
    Steps
    -0.05
    箫
    -0.05
    econom
    -0.05
    POSITIVE LOGITS
    åŀ¦
    0.05
     resetting
    0.05
     RESET
    0.05
    æ¡Ĩ
    0.05
     Caz
    0.05
     amounts
    0.05
    å¼ķ导ä¸ĭ
    0.05
    uh
    0.05
    Limits
    0.05
    oid
    0.05
    Activations Density 0.052%

    No Known Activations