© 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. 21977
    Prev
    Next
    INDEX
    Explanations

    secret, hidden, closet

    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
    cene
    -0.06
    immel
    -0.06
    ogl
    -0.06
    éļł
    -0.06
    oucher
    -0.06
    æŃ³
    -0.05
    yme
    -0.05
    Desk
    -0.05
    åįģåĽĽäºĶ
    -0.05
    olu
    -0.05
    POSITIVE LOGITS
     lest
    0.06
    åºľ
    0.06
    èĮĥåĽ´
    0.05
    اØŃت
    0.05
    ä»ħ
    0.05
    åĨħéľĢ
    0.05
    ä»ħéĻIJ
    0.05
    à¹Ģà¸Ķียว
    0.05
    åĮºåĪ«äºİ
    0.05
     mari
    0.05
    Activations Density 0.004%

    No Known Activations