© 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. 18449
    Prev
    Next
    INDEX
    Explanations

    explore or investigate

    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
    wards
    -0.06
    experimental
    -0.06
     ÑģпÑĢо
    -0.05
    iable
    -0.05
    ç²ĹæĶ¾
    -0.05
    specified
    -0.05
     пÑĢизÑĭ
    -0.05
    WARDS
    -0.05
    弯路
    -0.05
     коÑĢиÑģÑĤÑĥ
    -0.05
    POSITIVE LOGITS
    -ready
    0.07
    yst
    0.06
     hãi
    0.06
    éķĬ
    0.06
     ante
    0.06
    éĹ®é¢ĺ解åĨ³
    0.05
    åĽ¢çļĦ
    0.05
    主ä¹ī
    0.05
     FEMA
    0.05
    olja
    0.05
    Activations Density 0.001%

    No Known Activations