© 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. 18298
    Prev
    Next
    INDEX
    Explanations

    programming language imports

    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
    ript
    -0.06
    icc
    -0.06
    ×Ĺ×ķת
    -0.06
     Kamar
    -0.06
    omatis
    -0.06
    decor
    -0.06
    æ°ĶçļĦ
    -0.06
    她è¿ĺæĺ¯
    -0.06
     pérd
    -0.06
    èĢĮéĻį
    -0.06
    POSITIVE LOGITS
    edr
    0.05
    H
    0.05
    araoh
    0.05
    è¾¾
    0.05
    anh
    0.05
    S
    0.05
     "
    0.04
    J
    0.04
     طرØŃ
    0.04
    使çĶ¨è¿ĩç¨ĭä¸Ń
    0.04
    Activations Density 0.060%

    No Known Activations