© 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. 17784
    Prev
    Next
    INDEX
    Explanations

    dry mixture ingredients

    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
    ons
    -0.05
    ifa
    -0.05
    ange
    -0.05
    å¤ļæ±ģ
    -0.05
    اÙĨÙĪ
    -0.05
    ang
    -0.05
    on
    -0.05
    .super
    -0.05
    ón
    -0.05
    usti
    -0.05
    POSITIVE LOGITS
     brut
    0.06
     Jep
    0.06
     raffin
    0.06
     Ayah
    0.06
    ä»ĺ
    0.06
    ietf
    0.06
     theirs
    0.06
     bá»ķ
    0.06
    yé
    0.06
     Adriano
    0.06
    Activations Density 0.003%

    No Known Activations