© 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. 19388
    Prev
    Next
    INDEX
    Explanations

    `Test` followed by `_import`, `Requires`, `_get`, `Create`, `mock`, `should`, `Set`

    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
    abouts
    -0.06
    ophile
    -0.06
    å¾®
    -0.05
    å®īæİĴ
    -0.05
    ungsk
    -0.05
    itness
    -0.05
    ader
    -0.05
    /Q
    -0.05
     tested
    -0.05
    aset
    -0.05
    POSITIVE LOGITS
    ellige
    0.06
    engg
    0.06
    åľ¨æ²¡æľī
    0.06
     бÑĭваÑİÑĤ
    0.05
    们对
    0.05
    ellig
    0.05
    éĽĨéĶ¦
    0.05
    (','
    0.05
    æľįåĬ¡æ°´å¹³
    0.05
     kısm
    0.05
    Activations Density 0.042%

    No Known Activations