© 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. 20933
    Prev
    Next
    INDEX
    Explanations

    range between 0 and

    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
    åĩĨ
    -0.06
    æºĸ
    -0.06
    _compat
    -0.06
    wany
    -0.05
    åĢĴ
    -0.05
    Prompt
    -0.05
     leeft
    -0.05
    PATCH
    -0.05
    usso
    -0.05
    ionato
    -0.05
    POSITIVE LOGITS
    èĬ¸
    0.05
    èµ°èµ°
    0.05
    alls
    0.05
    åıĪä¸Ģ个
    0.05
     terce
    0.05
    ebol
    0.05
    æĭīæĿĨ
    0.05
    åĩŃåĢŁ
    0.05
     verge
    0.05
    bia
    0.05
    Activations Density 0.004%

    No Known Activations