© 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. 21306
    Prev
    Next
    INDEX
    Explanations

    as followed by a noun or phrase

    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
    æ¸Ī
    -0.06
    edian
    -0.06
    大ä¸įäºĨ
    -0.06
    onger
    -0.06
    uskan
    -0.06
    ä¾ĽåĽ¾
    -0.06
    >>)
    -0.06
    ï¼Łï¼ī
    -0.05
    ?',
    -0.05
    unica
    -0.05
    POSITIVE LOGITS
    uy
    0.06
     then
    0.06
    asse
    0.05
    UY
    0.05
    ira
    0.05
     renunci
    0.05
    åħ¶åIJį
    0.05
    aur
    0.05
     além
    0.05
    yeah
    0.05
    Activations Density 0.021%

    No Known Activations