© 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. 17268
    Prev
    Next
    INDEX
    Explanations

    require statements

    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
    vole
    -0.06
    ofil
    -0.06
    ä¾
    -0.05
    ariance
    -0.05
    worthy
    -0.05
    ä¼łæĴŃ
    -0.05
     tro
    -0.05
    ä¼į
    -0.05
    èĤ¿
    -0.05
     Spawn
    -0.05
    POSITIVE LOGITS
    duct
    0.07
    acon
    0.06
    ustin
    0.06
    usta
    0.06
    esus
    0.06
    ansa
    0.06
    ansch
    0.06
    anic
    0.06
    auc
    0.05
    shipment
    0.05
    Activations Density 0.007%

    No Known Activations