© 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. 21361
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ever
    -0.07
    haupt
    -0.06
    à¯Ī
    -0.06
    ÙĬØ©
    -0.06
    ily
    -0.06
    èī²åĪĹ
    -0.06
    аÑİÑĤ
    -0.06
    éf
    -0.06
    ÑıÑĤа
    -0.06
    ен
    -0.06
    POSITIVE LOGITS
    igr
    0.05
    åı¯èĥ½æĺ¯åĽłä¸º
    0.05
    ãģĦãģĦ
    0.05
    folge
    0.05
    tanto
    0.05
     أجÙĦ
    0.05
    次çļĦ
    0.05
     presum
    0.05
    ****
    0.05
    नाव
    0.05
    Activations Density 0.013%

    No Known Activations