© 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. 21953
    Prev
    Next
    INDEX
    Explanations

    roles and company positions

    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
     figure
    -0.05
    feuille
    -0.05
    åĬłéĩĮ
    -0.05
    figure
    -0.05
     equ
    -0.05
    èĩªä¿¡
    -0.05
    ä½ĵç³»
    -0.05
    åıĹæįŁ
    -0.05
     tut
    -0.05
    ä½ľä¸º
    -0.05
    POSITIVE LOGITS
     conlle
    0.07
    丰å¯Įå¤ļæł·çļĦ
    0.06
    nze
    0.06
    弥漫çĿĢ
    0.06
    ìĬµ
    0.06
    hower
    0.06
    OOM
    0.06
    eno
    0.06
    stv
    0.06
    大èĥľ
    0.06
    Activations Density 0.015%

    No Known Activations