© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20552
    Prev
    Next
    INDEX
    Explanations

    frame number or values

    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
    ively
    -0.06
    entially
    -0.06
    ׼×Ŀ
    -0.06
    еÑģÑĤвен
    -0.06
    rael
    -0.06
    ège
    -0.06
    нÑĥ
    -0.05
    ÑĤеÑĢо
    -0.05
    ses
    -0.05
    ington
    -0.05
    POSITIVE LOGITS
    Ø«ÙĬÙĦ
    0.07
    娩
    0.07
    stances
    0.07
    nable
    0.07
    stile
    0.06
     lunak
    0.06
    ìĽĮíģ¬
    0.06
    žia
    0.06
    igts
    0.06
     thù
    0.06
    Activations Density 0.012%

    No Known Activations