© 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. 17075
    Prev
    Next
    INDEX
    Explanations

    code blocks and structures

    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
    tr
    -0.05
    è¯ģæĺİ书
    -0.05
    flu
    -0.05
    ire
    -0.05
    -A
    -0.05
    çļĦè¿ĺæĺ¯
    -0.05
    inue
    -0.05
    âĢij
    -0.05
    are
    -0.05
    que
    -0.05
    POSITIVE LOGITS
    duto
    0.07
    foro
    0.07
    ÃijO
    0.07
    omt
    0.07
    elado
    0.07
    orage
    0.06
    ULER
    0.06
    voz
    0.06
     Redação
    0.06
    dze
    0.06
    Activations Density 0.007%

    No Known Activations