© 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. 17381
    Prev
    Next
    INDEX
    Explanations

    manufacturing, building, and developing things

    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
    دÙĦ
    -0.06
    çģ«éĢŁ
    -0.06
    ierna
    -0.06
    å¸Īå¾Ĵ
    -0.06
    nance
    -0.06
    ÑīиÑĤе
    -0.06
    alÄĥ
    -0.05
    ADDING
    -0.05
    æīĢè§ģ
    -0.05
    çĶ³ãģĹ
    -0.05
    POSITIVE LOGITS
    elv
    0.05
    ul
    0.05
    J
    0.05
    åĽº
    0.05
    èĥİ
    0.05
    v
    0.05
    çĶ¨æĿ¥
    0.05
    arm
    0.05
    isans
    0.05
    æŃ£ä¸Ń
    0.05
    Activations Density 0.001%

    No Known Activations