© 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. 17348
    Prev
    Next
    INDEX
    Explanations

    Let, Calculate, Suppose

    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
    ^
    -0.06
    hs
    -0.05
    ness
    -0.05
    !
    -0.05
    ide
    -0.05
    Âł
    -0.05
    °
    -0.05
    |
    -0.05
    Ì
    -0.05
    ↵↵
    -0.05
    POSITIVE LOGITS
    imiz
    0.08
    ä¸Ĭãģ®
    0.08
    utilise
    0.08
    âĢ¦ãĢį
    0.08
    ãĤīãĤĵ
    0.07
    åĪĨ许
    0.07
     richies
    0.07
    âĢ¦*
    0.07
    éĢļ讯社
    0.07
     ÙħØ«
    0.07
    Activations Density 0.145%

    No Known Activations